Autonomous Experimentation

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 114% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 93

Oct 8, 2026cs.AI

LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models

Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with minimal human oversight. Yet identifiability is often overlooked: when a plateau is reached, the agent needs to know whether it is not yet capable enough or the model simply is not identifiable from the data, in which case no amount of further experimentation of the same kind can help. We propose the Identifiability-Driven Experimental Agent (LLM-IDEA) for closed-loop discovery with an identifiability engine that returns a three-way plateau verdict: capability limit, resolvable within the design class, or certified exhausted. On ODEBench, 60 of the 62 systems with free constants are identifiable at round 0; the RC circuit is certified exhausted for every experiment that protocol can run, and a harvesting model is resolvable by one added initial condition. The identifiability engine reproduces known verdicts on Lotka-Volterra, Van der Pol, Lorenz, and a pharmacokinetic model, where it recommends the intravenous arm pharmacologists use, and it ranks the depth scorer of our own benchmark last among four observation designs. On the DiscoverPhysics benchmark, it finds two public worlds whose explanation rubric rewards a distinction no legal experiment can make, and every model there with accurate trajectories failed the explanation grade (15 of 15, against 5 of 9 in identifiable worlds, p = 0.012). On the Alien Universe, a two-body testbed we propose in which a force law switches between a provably non-identifiable and an identifiable protocol, LLM-IDEA on the identifiable protocol reaches discovery depth at least three on 8/8 seeds versus 1/8 without it. An autonomous discovery agent can thus compute, rather than guess, whether a plateau calls for more search, a better experiment of the same kind, or a different kind of experiment.

Surya Shetty, Ulisses Braga-Neto

Texas A&M University · Polara Labs Inc.

Autonomous Scientific Discovery Autonomous Experimentation Parameter Identifiability

Oct 7, 2026cs.LG

RSIGym: A Flexible Environment for Recursive Self-Improvement

Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure. Existing settings often leave agents to rebuild routine infrastructure or restrict exploration to individual components. We introduce RSIGym, an agent-native research environment based on Everything as a Service (EaaS). RSIGym exposes training, inference, rollout, evaluation, and sandbox execution through reusable services, with shared budget and permission controls supporting Data, Harness, and Joint improvement tracks. This design enables agents to investigate individual interventions and jointly optimize data, training settings, and execution harnesses within the same environment. We define RSI-Index as the mean fraction of the remaining performance gap closed across five benchmarks covering software engineering, terminal interaction, mathematics, scientific reasoning, and skill-based tasks. Comparing six frontier research models in independent Joint runs, Opus 5 achieves the highest RSI-Index of 0.4809 under a $500 platform-service budget per benchmark run. Its selected systems improve all five benchmarks, raising SWE-bench Verified from 17.67% to 50.33% and AIME from 31.67% to 97.78%. Additional experiments examine DSH-harness refinement, budget variation, and restricted network access, while recorded trajectories reveal how agents diagnose failures and select candidates. We open-source the full RSIGym codebase and results to support reproducibility and further research.

Fanqing Meng, Lingxiao Du, Haocheng Lu +6

Evolvent AI · National University of Singapore

LLM Agent Self-Improvement Recursive Self-Improvement Autonomous Experimentation Agent Harness Optimization AI Agent Benchmarks

Oct 5, 2026cs.LG

Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents

Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that independent runs of the same agent on the same task often plateau at substantially different scores, with gaps that persist even after considerable additional compute. Embedding their candidate artifacts by functional similarity provides further evidence that trajectories remain in localized regions of the solution space, which we call idea basins. To help agents escape these basins, we study a simple periodic intervention, fork-and-flush. Our method forks the agent into parallel trajectories, each inheriting the accumulated workspace but starting with a fresh chat context. After running each trajectory for a fixed horizon, the agent continues from the highest-scoring one. Across 13 long-horizon research and engineering tasks, with individual agent runs lasting up to several days, fork-and-flush outperformed the single-run and best-of-N baselines by a relative improvement of 66.0% and 44.4%, respectively, on the min-max normalized average score under an equal compute budget.

Ziyang Cai, Christos Ziakas, Vasilis Kontonis +5

Microsoft Research

Local Search Long-Horizon Agent Tasks Autonomous Experimentation Autonomous Research Agents

Oct 1, 2026cs.LG

MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection

Benchmark gains are often mechanism-ambiguous: reproducing an improvement does not by itself identify why it occurs. We study finite-library mechanism discrimination, where posterior-weighted candidate mechanisms, executable probes, and a limited experimental budget define a sequential experiment-selection problem. MECHVAR selects the next probe by maximizing the posterior-weighted variance of its predicted responses. Under a shared-Gaussian predictive model, this score is exactly proportional to the classical Box--Hill posterior-weighted pairwise-KL criterion, yet it admits O(KE) vectorized rescoring and a transparent additive audit over mechanism pairs. A local expansion further links the score to expected information gain (EIG) when predicted response separations are small. In a 25-block stress audit, MECHVAR outperforms confirmation-first in several moderate misspecification regimes, while its primary comparisons with EIG remain statistically unresolved. In a held-out Digits loop, normalized mechanism-identification AUC is 0.8975 for MECHVAR, 0.7825 for a score-greedy policy, and 0.9092 for EIG. At K = 100, E = 200, median single-thread full-library scoring is 10.36 microseconds for MECHVAR versus 57.69 ms for six-node quadrature EIG in the recorded environment. MECHVAR therefore provides a lightweight, auditable acquisition rule for finite-library experiment selection when a shared predictive scale is a defensible approximation.

Yifan Guo

Stony Brook University

Bayesian Experimental Design Autonomous Experimentation

Oct 1, 2026cs.AI

AbsorbEvo: An Agentic Framework for Autonomous Inverse Design of Microwave Absorbers

Designing high-performance microwave absorbers requires specialized expertise in electromagnetic theory, materials science and simulation programming, and entails time-consuming optimization. Here, we present AbsorbEvo, an agentic framework for autonomous inverse design that translates natural-language performance objectives into designs verified by full-wave simulations. Its candidate evolution strategy integrates language reasoning, physics-based prediction and historical feedback. A large language model proposes the directions and magnitudes of parameter adjustments based on task objectives and computational history. The system combines directed increments with global sampling to generate candidates and uses a low-cost predictive model as a physics prior to rank them. Only high-ranking designs undergo full-wave simulation. Results passing physical validity checks are used to evaluate performance and guide subsequent search. Experience from training tasks is further distilled into textual skills, which are independently validated before use in new tasks. Under identical proposal budgets on held-out AbsorbBench-36 tasks, AbsorbEvo achieved a task success rate of 79.17%, versus 25.00% for a generic agent and 12.50% for random search. Its mean best coverage was 0.7816, compared with 0.6434 and 0.6448, respectively. By integrating language reasoning and physics-based feedback into design decisions, AbsorbEvo provides a methodological foundation for natural-language-driven autonomous inverse design of microwave absorbers.

Zhicheng Feng, Yubo Zhao, Xuefeng Yao

Department of Engineering Mechanics, Applied Mechanics Lab, Tsinghua University, Beijing 100084, P. R. China

Large Language Model-Guided Optimization Natural Language to Optimization Modeling Inverse Design Autonomous Experimentation

Sep 30, 2026cs.AI

Experimental Experience Modeling for Autonomous Research

Autonomous research agents can generate hypotheses and conduct experiments, but experimentation remains a major source of computational cost. A fundamental challenge is deciding which experiments are worth running, particularly when prior evidence is insufficient to resolve uncertainty. Yet current research agents lack a systematic way to leverage experimental experience when making such decisions. We introduce Experimental Experience Modeling (EEM), a framework for making informed experimental decisions by acquiring, reusing, and accumulating experimental experience. EEM extracts decision-relevant records from earlier experimental trajectories, distills them into reusable experience, and organizes them in an experience library. For a new experimental decision, EEM retrieves relevant historical experience and assesses whether it provides sufficient support for deciding whether a candidate direction warrants further investment. When historical experience is insufficient, EEM conducts a targeted, low-cost pilot experiment to acquire the missing decision-relevant experience on demand. It then combines this newly acquired experience with retrieved historical experience to determine whether the direction warrants full-scale evaluation, which requires substantial resources. The resulting experimental outcomes are further distilled into reusable experience, allowing the library to continually grow through iterative accumulation. Experiments on autonomous research benchmarks show that EEM improves research performance while reducing model interaction overhead, demonstrating the value of reusing accumulated experience and acquiring additional experience only when needed.

Wenda Wei, Yingchen Zhang, Ruqing Zhang +3

State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +1

AI Agents for Scientific Discovery Autonomous Experimentation Autonomous Research Agents

Sep 30, 2026cs.AI

Autoresearch in Mixed-Integer Linear and Nonlinear Programming

Despite recent progress in autoresearch, applying it to practical operations research problems, typically formulated as NP-hard mixed-integer linear or nonlinear programs (MILPs or MINLPs), remains challenging because effective research requires systematically managing competing ideas and long-horizon experimental trajectories. We introduce AutoMIP, a reusable agent skill for organizing long-horizon autoresearch in mixed-integer programming through idea pooling and algorithm tree search. AutoMIP maintains a persistent pool of complementary candidate ideas while organizing executable experiments into an algorithm tree, enabling the agent to preserve unexplored hypotheses, refine promising algorithms, and switch to alternative methodological directions based on historical states. On MILP and MINLP benchmark cohorts, AutoMIP achieves the highest final success rates among the evaluated autoresearch frameworks. On MIPLib, AutoMIP discovers new best solutions for 31 of 60 instances, surpassing existing autoresearch frameworks. On MINLPLib, it achieves new best solutions for 52 of 60 instances. Ablation studies further demonstrate the complementary contributions of idea pooling and algorithm tree search, highlighting the importance of jointly maintaining diverse research ideas and structured experimental trajectories for long-horizon autoresearch.

Yuwei Gu, Yaoxin Wu, Tong Guo +2

Chengdu University of Information Technology · Eindhoven University of Technology · Nanyang University of Technology +2

Automated Algorithm Discovery Mixed-Integer Linear Programming Constrained Optimization Autonomous Experimentation Autonomous Research Agents

Sep 30, 2026cs.RO

SimEX: Simulation-Integrated Robotics AutoResearch

Coding agents powered by large language models (LLMs) have shown remarkable abilities to autonomously reason about and achieve goals in the digital world. However, bringing this success to the physical world remains challenging. On the one hand, direct generation methods (e.g., Code as Policies) often suffer from the LLMs' insufficient understanding of robots and physical environments. On the other hand, iterative trial-and-error tuning in the physical world (e.g., physical autoresearch) induces significant experimental cost and safety concerns. We introduce SimEX: Simulation-Integrated Robotics AutoResearch, an autoresearch framework that tightly integrates simulated experimentation, enabling coding agents to efficiently acquire physical capabilities for controlling real robots. SimEX operates in two stages. First, the agent conducts open-ended probe-and-optimize iterations in simulation, developing a robot toolbox with robust and generalizable capabilities. Second, the agent adapts the toolbox and the simulator together through only a few physical trials: each trial corrects the simulator, and the corrected simulator is used to diagnose failures and screen candidate repairs. We evaluate SimEX extensively in sim-to-sim settings and on physical robots. On challenging real-world manipulation tasks including towel folding, barcode scanning, and plate manipulation, SimEX enables coding agents to efficiently acquire robot skills without any demonstration and with only 10 minutes of real-robot interaction. These results suggest that simulation can be a critical component in achieving physical intelligence, not only as a source of training data that must closely replicate the real world, but also as a roughly correct laboratory where a coding agent develops the knowledge and procedures needed to act on the robot. More details and robot videos at https://robo-simex.github.io/

Jiaheng Hu, Roberto Martin-Martin, Peter Stone +3

Amazon FAR (Frontier AI & Robotics) · The University of Texas at Austin · Carnegie Mellon University

Robot Skill Learning Robotics Simulation Sim-to-Real Transfer Robotic Manipulation Autonomous Experimentation

Sep 28, 2026cs.AI

RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement

Recursive self-improvement (RSI) seeks to enable AI systems to participate in improving their own capabilities. A concrete pathway is autonomous model development, where agents iteratively explore post-training strategies to improve a base model. This setting faces two challenges: agents may exploit open-ended experimental actions through hacking, and repeated experimentation may lead to strategy lock-in, where an early direction is refined rather than reconsidered. We introduce RSI-Master, which addresses the two challenges at two levels: regularize step-wise actions, avoiding hacking behaviors, and promote well-structured exploration of research directions, avoiding strategy lock-in. RSI-Master consists of an Experiment OS, which enables regularized experimental actions and maintains persistent, traceable experimental records, and Reviewer-Guided Research Orchestration, which organizes Workers and Reviewers in a dynamically growing research DAG. Workers explore diverse research directions and Reviewers compare evidence across related experiments for subsequent explorations. On PostTrainBench with Qwen3-4B-Base, it averages 54.49 versus 46.53 for the strongest agent baseline, with a 0.0% hacking rate. Scaling to 35B model, RSI-Master surpasses the human-developed Instruct model on LiveCodeBench-v6 (41.21 vs. 37.36) and SciCode, and reaches a nonzero score on HorizonMath, a benchmark of unsolved research problems on which most frontier models score near zero.

Yaxin Du, Xiyuan Yang, Zhifan Zhou +10

Shanghai Jiao Tong University · Carnegie Mellon University · University of Waterloo

Language Model Post-Training Self-Improving Agents Autonomous Experimentation Autonomous Research Agents

Sep 28, 2026cs.IR

PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems

AutoResearch improves systems through iterative experimentation: agents propose candidate modifications, evaluate them, and use the results to guide subsequent exploration. Applying this paradigm to industrial search presents two challenges. (1) Common AutoResearch approaches follow a keep-if-better rule, retaining the highest-scoring candidate for subsequent experiments. Under non-stationary traffic, transient gains may be mistaken for persistent improvements, impairing reliable accumulation of search knowledge. (2) Candidate modifications can be evaluated at multiple fidelity levels, from low-cost proxies to online validation, differing in cost, objective alignment, and statistical reliability. Existing methods rely on individual signals or task-specific procedures, lacking a unified basis for using evidence across levels to guide search. We introduce Progressive Evidence-Based AutoResearch (PEAR) with two complementary components. Evidence-driven AutoResearch maintains an independent, hypothesis-guided research state for each strategy task within a predefined objective and intervention scope. Each state evolves through a Plan-Execute-Evaluate-Update transition that links experimentation to context-aware evidence interpretation and hypothesis revision. Confidence-Gated Verifier Ladder organizes evaluation into four levels of increasing fidelity: Offline Replay, Shadow-Traffic Evaluation, Rapid Online Evaluation, and Decision-Grade Online Evaluation. A unified confidence-based gate promotes candidates only when evidence supports a statistically significant positive effect, enabling broad low-cost exploration while reserving costly online experiments for promoted candidates. In a real-world industrial search system, strategies optimized with PEAR significantly increased Main Order/DAU by 2.7336% and 3.2957% relative to their respective baselines in two A/B experiments.

Yifan Wang, Shipeng Zhu, Fei Xiong +6

Global E-Commerce Agentic Search Team

Information Retrieval Sequential Hypothesis Testing Autonomous Experimentation Autonomous Research Agents

Sep 27, 2026cs.LG

ALDER: Discovering the Laws of a World by Acting in It

Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such as equations. Yet methods that rely on a fixed set of trajectories cannot distinguish equally good competing hypotheses, while searches over a fixed set of predefined candidates cannot discover equations outside the initial hypothesis space. We introduce ALDER (Action-guided Law Discovery, Evaluation, and Revision), a method that actively proposes novel experiments to test and revise models. Specifically, ALDER proposes parametric equations; a numerical optimizer fits their coefficients; an independent verifier tests these candidates on held-out data. To distinguish between competing valid hypotheses, a cost- and safety-aware selector queries interventions, in the form of novel experiments. The resulting counterexamples update the evidence ledger and guide the next structural revision, while incompatible laws are discarded. Across an in-house benchmark, ODE equation discovery tasks, and robotic experiments, ALDER discovers laws beyond its initial formula set, repairs failed model proposals, distinguishes fixed candidate models with fewer interactions, and improves out-of-distribution prediction. Furthermore, given a current state and a target, ALDER selects control actions by solving the inverse problem defined by its validated world model. Together, these results show that explicit equation-based world models can be tested and revised through interaction, then naturally used to guide goal-directed control.

Teng Cao, Yu Deng, Quentin Delfosse +1

Technische Universität Darmstadt · Intrinsic · CS Department, TU Darmstadt +2

Scientific Discovery Action-Conditioned World Models Autonomous Experimentation

Sep 24, 2026cs.AI

Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems

Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation of AgentX's model research framework, which connects proposal development and model experimentation within sandboxes defined by business inputs and prediction tasks. AgentX-Model adopts a dual-agent architecture comprising a Research Agent and a Model Agent. The Research Agent develops independently reviewed proposals from papers and experimental findings, while the Model Agent conducts multi-round investigations and returns code, measurements, and unresolved questions. Using the returned results, the Research Agent selects a starting implementation and formulates the next research question, allowing subsequent experiments to build on earlier findings. We organize this continuing research around four actions: Reproduce, Follow-up, Composition, and Diagnose. The first three actions drive routine research, while Diagnose acquires the evidence needed to choose a repair, including for issues raised by business feedback and online evaluation, such as prediction bias measured by PCOC. Across the production evaluation, 560 of 636 completed model-changing experiments recorded AUC above their business baselines. As research continued, some experiments recorded AUC above every comparable ancestor in their lineages. The five latest online A/B evaluations across different business settings reported gains including 10-15% in acquisition efficiency, 15-20% in target-segment advertising spend, and 0.3-0.8% in watch time; the watch-time model used approximately 10% fewer FLOPs and parameters. A dependency-aware historical-replay benchmark further evaluates research allocation, with initial results showing no consistent efficiency gain from more complex scheduling when agents already analyze and select concrete candidates.

Shuang Yang, Zijie Zhuang, Changxin Lao +20

AI Agents for Scientific Discovery Long-Horizon Agent Evaluation Recommender Systems Autonomous Experimentation Autonomous Research Agents

Sep 23, 2026cs.AI

WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents

AI research agents must predict the effects of computational changes after budgeted experiments. WhatWorkedBench evaluates this experimental understanding through a delivered response surface of configuration scores. Agents inspect workflow code and buy measurements; exhaustive CPU references score conditional component effects, mean pair interactions, configuration choice, and delivery. The catalog spans 36 task conditions, 30 sources, 8 workflow families, and 1248 indexed configuration records, with 4,206 numerical controls. At eight purchased measurements plus two free anchors, pair-effect ridge selects an exact optimum on 15 of 22 sources; 13 of these cases have at least one conditional-effect error exceeding 10% of the task utility range. Shared-estimator comparisons measure acquisition and reconstruction on common observations. In a prospective typed study on 12 four-factor sources, DeepSeek Flash submits 12/12 direct tables and gains 0.147 recovery over a Gaussian process (GP) fitted to the same observations. Pro delivers 11/12 artifacts, with an all-attempt GP difference of -0.001 and a delivered-only difference of +0.063. On six prespecified new agent-evaluation sources, Flash and Pro gains are 0.149 and 0.074. In eight typed six-factor episodes, seven final tables satisfy verified code equivalences. Four fresh agents pass all six registered rules through named estimators and deliver consistent tables at 0.682 recovery versus 0.710 for separate direct-table runs. WhatWorkedBench links acquisition, inference, program structure, and delivery.

Jingjie Ning, Xueqi Li, Yibo Kong +1

Carnegie Mellon University · Tsinghua University

AI Agent Evaluation Active Learning AI Agent Benchmarks Autonomous Experimentation

Sep 16, 2026cs.LG

Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory

Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present Andromeda 2, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. Using a miniaturized automated laboratory at a matched budget, we benchmark it against Andromeda 1, a probabilistic optimization model deployed across dozens of live development projects, and a wet-lab design-of-experiments (DoE) campaign. For paclitaxel, Andromeda 2 achieved a 50% high-performance hit rate versus 17% for Andromeda 1 and 2% for DoE, and identified 12 formulations meeting all four target product profile (TPP) objectives versus 6 and 0, respectively. Median

AUC_{10-240}

was 70.1, 12.0, and 3.5 mg

\cdot

min/mL, while maximum AUC was comparable between Andromeda 2 and Andromeda 1. A selected full-TPP formulation achieved an apparent effective paclitaxel loading of

19 \pm 5\%

w/w at the first FaSSIF measurement, approximately 3.3-fold higher than the 5.7% w/w loading reported for a published paclitaxel S-SEDDS. A controlled ablation showed that access to structured in-house experimental evidence increased mean AUC by 34%.

Michael M. Craig, Riley J. Hickman, Yingshan Ma +3

Intrepid Labs, Toronto, Canada

Autonomous Experimentation Autonomous Research Agents Drug Discovery

Sep 16, 2026cond-mat.mtrl-sci

Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents

Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the output is a set of optimized samples, with the measurements reduced to predefined scalar objectives and the reasons behind success left unarticulated. Here we present SynAgent, a framework in which large language model agents operate an automated experimental system and maintain an explicit, revisable understanding of the synthesis process as the campaign's primary output. Starting with no predefined analysis pipeline, SynAgent adaptively generates analysis skills for newly acquired data and evolves this understanding through multimodal reasoning over experimental data such as X-ray diffraction patterns and electron micrographs. The evolution is guided by a verify-falsify scheme, in which the agent deliberately challenges its own hypotheses by testing conditions predicted to fail as well as those predicted to succeed. In a single campaign of 18 autonomous experiments using LiCoO2 (001) thin-film deposition as a testbed, SynAgent synthesized highly crystalline films and evolved an understanding of how the substrate temperature governs crystallization, discovering an abrupt threshold and a narrow optimal growth window at 650-690 °C. These results extend autonomous experimentation beyond optimized samples to testable, human-readable understanding.

Izumi Takahara, Kazunori Nishio, Akira Aiba +4

Institute of Industrial Science, The University of Tokyo, Tokyo 153-8505, Japan · Department of Chemistry, The University of Tokyo, Tokyo 113-0033, Japan · Rigaku Corporation, Tokyo 196-8666, Japan +1

LLM Agent Skill Learning Autonomous Scientific Discovery Multimodal Agents Large Language Model-Guided Scientific Discovery Autonomous Experimentation

Sep 14, 2026cs.CL

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration drives this process, yet managing and improving exploration strategies remains a major bottleneck. Current systems face a fundamental dilemma: fixed strategies fail to adapt as search spaces scale, while online policy optimization must navigate vast meta-search spaces under delayed, expensive feedback from long-horizon rollouts. We introduce \textsc{Dream-RSI}, a framework for scalable, recursively self-improving exploration. A lightweight orchestration layer makes exploration explicit and programmable while leaving the underlying base agent unchanged. Our key insight is that accumulated discovery history can act as a replay simulator over the realized search space. By dreaming within this simulator built from historical discovery trees, \textsc{Dream-RSI} obtains immediate, low-cost off-policy feedback to evaluate and refine exploration policies without repeated, expensive online evaluation. The improved policy is then redeployed online to drive further discovery, continuously expanding the simulator pool in a self-improving loop. Across 9 tasks in 4 domains, \textsc{Dream-RSI} achieves competitive quality and improves discovery efficiency in several settings.

Tong Zheng, Xidong Wu, Zheng Zhang +14

Google · University of Maryland, College Park · Google Deepmind +1

RL Exploration Self-Improving Agents Recursive Self-Improvement Autonomous Experimentation Off-Policy RL

Sep 11, 2026cs.CL

Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System

Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this paradigm to industry-scale recommendation models introduces two challenges: (1) long feedback loops, where model training can take days, making serial iteration prohibitively slow and requiring parallel exploration across multiple research directions; and (2) system complexity, where large configurations, fragile infrastructure dependencies, and multi-day GPU jobs require robust and recoverable execution. We present Auto-RecSys, an autonomous research system for long-horizon experimentation on industry-scale recommendation models. Auto-RecSys addresses these challenges through three harness designs: (1) distributed asynchronous execution for running multiple experiments in parallel across servers, (2) centralized cross-server memory for persistent and recoverable execution across sessions and failures, and (3) cognitive-procedural separation, where natural-language skill files guide LLM reasoning while deterministic scripts enforce operational correctness. Auto-RecSys further employs a dual-loop self-evolving architecture: an Execution Evolution Loop in which model-specific playbooks accumulate operational knowledge by recording failed attempts and crystallizing successful pipelines, and an Idea Evolution Loop in which experimental outcomes inform subsequent ideation. Evaluated on recommendation models, Auto-RecSys significantly reduces the human time required per experiment cycle and improves execution reliability as its playbooks mature.

Ming Li, Dai Li, Xuying Ning +11

Meta · University of Illinois Urbana-Champaign

Recommender Systems Long-Horizon LLM Agents Autonomous Experimentation Autonomous Research Agents

Sep 7, 2026cs.AI

La Agente 'Optima: Towards Agentic Self-Driving Laboratories

Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nevertheless often depends on human specialists who translate scientific objectives into executable closed-loop campaigns. Specialists adjust them as data and operating conditions change. Here, we present La Agente 'Optima, an agentic framework that constructs and supervises Bayesian optimization campaigns across computational and experimental systems while maintaining a persistent optimization state. By separating large language model (LLM) reasoning from executed campaigns, 'Optima runs repetitive optimization loops consistently, returns control to the agent only when progress requires interpretation or campaign revision, and keeps every decision auditable. We evaluate 'Optima across ablation studies, five digital discovery tasks, and two physical platforms. Throughout, 'Optima maintained executable campaigns as both the scientific problem and execution environment evolved. In a closed-loop contact angle optimization campaign, 'Optima identified and corrected a mid-run measurement failure, bringing the contact angle from 71.4 to 67.8 degrees, just above the 64-66 degree range. From this result, 'Optima correctly inferred that the target was likely unattainable with the available reagents and recommended changing the formulation. In a five-day multi-objective flow-chemistry campaign, 'Optima increased the yield from 30% to 59% over 23 experiments. Despite substantial inference costs, it cost less and used substantially less starting material than a human-directed campaign, while selecting a more mass-efficient operating point. These results show that LLM-based agents can make rigorous, long-running optimization campaigns accessible to domain scientists without specialist setup, expanding the scope of SDLs.

Marcel Müller, Jiaru Bai, Willi Gottstein +14

Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON2026 M5G 0C6, Canada · Acceleration Consortium, 700 University Ave., Toronto, ON M7A 2S4, Canada +11

Bayesian Optimization Large Language Model-Guided Optimization LLM Agent Orchestration Laboratory Automation Autonomous Experimentation

Aug 31, 2026q-bio.QM

Science sandboxes measure the scientific capability of AI agents

Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design better experiments. We introduce science sandboxes, a framework for studying this capability in AI agents through repeated cycles of experimentation, feedback, and hypothesis revision. Science sandboxes invite an agent to query the natural world in different ways, ranging from "wet" physical experiments, to "damp" predictive models trained on empirical data, to "dry" invented rules. By establishing a common experimental loop and a protocol for evaluating agents within it, science sandboxes allow assessment of both quantitative performance on specific metrics and qualitative scientific reasoning, across a spectrum of empirical verifiability. Here, we instantiate this framework in two biological settings, models of regulatory genomics and protein fitness prediction, and examine the capabilities of frontier agents. Across these settings, we could see when agents successfully optimized a quantitative metric without understanding the rules underlying the system. In particular, their scientific reasoning deteriorated when they encountered systems whose rules fell outside familiar biological priors. By highlighting such failure modes, science sandboxes make the frontier of scientific capability measurable and provide a controlled setting in which to study and ultimately expand it.

Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai +8

The Broad Institute of MIT and Harvard; Cambridge, MA 02142, USA. · Department of Biomedical Informatics, Harvard Medical School; Boston, MA 02115, USA. · The Jackson Laboratory; Bar Harbor, ME 04609, USA. +10

Protein Fitness Prediction AI Agent Evaluation AI Agent Benchmarks Autonomous Experimentation

Aug 18, 2026cs.AI

AutoResearch: Insight In, Hallucination Out

Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. In Idea Generation, AutoResearch continuously integrates emerging research signals with accumulated domain knowledge, identifies transferable mechanistic insights, and uses multi-model generation and cross-review to produce grounded, testable research plans. In Idea Execution, coordinated agents decompose these plans into experiments, iteratively implement and diagnose them, and employ independent evidence-based review before accepting research conclusions. Across representative settings in cross-modal retrieval, systems optimization, and benchmark-driven machine learning, AutoResearch turns generated ideas into measurable progress, detects and corrects unreliable experimental results, and makes evidence-conditioned decisions to continue, revise, or terminate research directions. For example, on RSICD benchmark, an AutoResearch-generated idea improves mean Recall from 32.84 to 34.69, while recording only 5 audit-confirmed issue events compared with 11-27 for other autonomous research systems. These results demonstrate a research process in which meaningful insight is grounded before experimentation and conclusions are grounded before acceptance: Insight In, Hallucination Out.

Xiang Liu, Qumeng Sun, Bruno +3

Infinite Evolution Lab, EvoMap

Scientific Hypothesis Generation Research Idea Generation Evidence-Grounded Generation Scientific Workflow Automation Autonomous Experimentation Autonomous Research Agents

Aug 13, 2026cs.CL

AQuA: Recursively Self-Improving Quantitative Trading Research Agents

We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the hypotheses and candidates proposed in later iterations. We present AQuA, which comprises two separate language-model-driven research systems: one for symbolic factor discovery and one for trainable model development. Each system records experimental results and uses them to guide subsequent proposals. Each operates in a fixed sandbox, which fixes the data splits, feature and label definitions, and evaluator while allowing the model to act only through constrained factor expressions or configuration diffs. The factor system, a manager-mediated multi-agent pipeline, discovers and combines factors into a signal that reaches a combined validation information coefficient of about

0.190

on a crypto universe. The model system, a config-driven loop over a hybrid time-series architecture, reaches a per-stock information coefficient of

+0.0843

on US equities and converts it into a threshold long/short strategy with a held-out Sharpe of up to

+2.50

at a two-leg cost. The strategy is positive in every year from 2021 to 2025.

Jiacheng Guo, Suozhi Huang, Yunlong Gao +5

Princeton University · Ant Group · Stanford University

Quantitative Finance Automated Algorithm Discovery Self-Improving Agents Recursive Self-Improvement Autonomous Experimentation Autonomous Research Agents+1

Aug 11, 2026cs.AI

ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation

Autonomous chemistry increasingly depends on environments in which agents can repeatedly act, observe, and adapt.Physical laboratories provide essential real-material evidence but are costly to repeat and difficult to use for tightly matched interventions, whereas most digital environments keep the underlying experimental world largely fixed. We introduce ChemWorld, a programmable chemical environment in which reusable process and observation components are compiled into executable worlds. ChemWorld separates the public experimental contract available to an agent from evaluator-owned chemical and material laws. Researchers can therefore vary world composition and operating conditions, or change a single hidden law while holding the public task and interaction conditions fixed. Transactional execution records operations, failures, resource changes, and state transitions, allowing complete environment-action trajectories to be replayed exactly and audited. Full-census qualification covered the reference registry, 52 generated compositions, and module, interface, compilation, and invalid-action tests. Eight deterministic experimental cases demonstrated shared lifecycle semantics, failure recovery, and exact replay, while six parent-child world-fork pairs isolated the effects of single private-law interventions under matched public conditions. An independent agent also completed a full lifecycle in a non-reference world through the same public interface. Within the declared component and model domain, ChemWorld provides a controlled and replayable substrate for studying experimentation across systematically varied chemical worlds, complementary to physical-laboratory evidence and calibration.

Jiangjie Qiu, Yijun Li, Xiaonan Wang

Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials, State Key Laboratory of Chemical Engineering and Low-Carbon Technology, Department of Chemical Engineering, Tsinghua University, Beijing 100084, China

AI Agents for Scientific Discovery Scientific Reproducibility Autonomous Experimentation

Aug 10, 2026cs.AI

Agentic Auto-Research is Fuzz Testing

Autonomous research agents can generate experiments faster than researchers can validate them. Researchers have responded by scaling the proposer and ranking more samples with a learned judge or human reviewers. We argue that this generate-and-rank paradigm misses the problem of sparse feedback. Within a declared research problem, an agent follows the control loop of a greybox fuzzer: it proposes a candidate, executes it, observes feedback, and chooses what to try next. A fuzzer rarely finds a bug, but coverage makes partial progress observable on every execution. Fuzzers then use that signal to mutate inputs and allocate effort, rather than only to rank completed runs. Auto-research needs the same two capabilities. First, each experiment should expose a cheap, dense signal of epistemic progress before final scientific validation is available. Second, that signal should determine the next intervention so that the agent searches rather than repeatedly samples. Because the optimized progress signal is guidance rather than a verdict, final validation must still decide what counts as a discovery using evidence protected from adaptive reuse. We propose controlled tests of whether candidate signals predict validated progress, whether feedback-directed search yields more validated discoveries per unit cost than repeated sampling, and whether protected validation reduces false discoveries. Feedback architecture, not only generation, is a central bottleneck in auto-research.

Yifeng He, Jicheng Wang, Yinzhe Zhao +2

University of California, Davis · ARA Lab · Zhejiang University +2

AI Agents for Scientific Discovery Autonomous Experimentation Autonomous Research Agents

Aug 10, 2026cond-mat.mtrl-sci

Multitask Scanning Probe Microscopy

Scanning probe microscopy provides nanoscale access to structural, electrical, electromechanical, magnetic, and mechanical properties of materials. Its increasing use for wafer-scale characterization and combinatorial materials exploration creates a need to distribute measurements efficiently across large spatial domains. This is particularly important when available modalities differ in acquisition time and potential for tip and sample damage, making exhaustive multimodal mapping over spatial grids impractical. Here, we demonstrate multitask scanning probe microscopy, a live, closed-loop workflow in which a multitask Gaussian process learns spatial and cross-modal relationships and autonomously selects both the next measurement location and the next experimental protocol. The approach is implemented on an automated large-sample atomic force microscope and demonstrated on a composition-spread AlScN wafer using tapping-mode and Dual AC Resonance Tracking (DART) measurements. Paired initial measurements establish the relation between the tasks, after which noncoincident measurements are used to update both response landscapes. The resulting workflow extends active learning in scanning probe microscopy from spatial sampling to autonomous allocation of measurement modalities and provides a basis for combining rapid, weakly perturbative imaging with slower contact, electrical, electromechanical, magnetic, or spectroscopic measurements.

Aditya Raghavan, Yu Liu, Ian Mercer +2

University of Tennessee, Knoxville, TN, USA · 2Pennsylvania State University, University Park, PA, USA

Active Learning Multi-Task Learning Autonomous Experimentation

Aug 10, 2026cs.AI

Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science

As AI agents are increasingly deployed in complex and new environments, knowing the conditions that influence their behavior becomes an indispensable step for their reliable and safe deployment. Yet causal behavioral evaluation of AI agents remains manual and labor-intensive. We introduce Abs2Sim and AEROBAT, a system of methods that support causal behavioral evaluation of AI agents via automated behavioral science. Given a user-specified target behavior, the methods automatically execute a full pipeline of behavioral science research---generating hypotheses about the behavior, designing and executing controlled experiments, making behavioral assessments, analyzing the results, and writing reports. For 12 target behaviors, the methods generated and tested 73 hypotheses: designing 1,160 controlled experiments and executing 22,954 simulation rounds in total. Moderate-to-strong statistical evidence emerged for 30 hypotheses, revealing potential modulators of AI behavior. In sum, our results demonstrate that automated behavioral science can extend the reach of behavioral evaluation of AI agents.

Soo Yong Lee, Jongha Lee, Jaewan Chun +8

KAIST, Kim Jaechul Graduate School of AI · Yale, Department of Psychiatry · University of Haifa, School of Public Health +3

AI-Assisted Scientific Research AI Agent Evaluation Autonomous Experimentation

Aug 7, 2026physics.acc-ph

Autonomous discovery of accelerator commissioning algorithms

Simulated commissioning has become essential for de-risking modern light-source design and commissioning, but the procedures being simulated are still designed entirely by human experts. Their labor-intensive redevelopment after lattice changes makes such studies hard to repeat and limits their use during early design iteration. This Letter demonstrates a closed research loop in which a language-model agent writes commissioning code, tests it in simulation, and improves the algorithm from the results. Applied to RF beam capture in the ALS-U accumulator-ring model, the loop substantially improves a working expert procedure and can construct a working one from a minimal starting point, with more capable models succeeding from less initial code. Extending the same framework to multiple objectives produces 16 non-dominated algorithms spanning physically distinct trade-offs between rapid beam capture and correction of seeded machine errors. This reframes commissioning studies from evaluating human-designed procedures toward a mode in which agents participate directly in discovering accelerator algorithms.

Thorsten Hellert

Lawrence Berkeley National Laboratory · Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA

Automated Algorithm Discovery Large Language Model-Guided Scientific Discovery Autonomous Experimentation

Aug 6, 2026cs.AI

OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agents

Autonomous agents choose actions using scores that may not reflect experimental success. We developed OPERA, an operator-residual framework for optical experiments. It represents experimental actions as optical operators and evaluates their outcomes using physically interpretable residuals. Operators specify executable changes to measurement, control or reconstruction, while residuals report departures from specified physical conditions. The agent uses both to select, combine or generate operators, and physical performance is evaluated independently against a withheld reference. Across three optical tasks, score-only feedback produced score increases without physical improvement in 23.6--39.0% of decisions, compared with 0.9--1.9% for operator-residual feedback. Operator-residual feedback increased the probability of reaching and maintaining task targets and reduced experimental budgets. Protocols selected in digital twins were transferred to three optical instruments, and repeated experiments showed a lower projection budget in structured-light reconstruction. Together, operators and residuals guide autonomous decisions using measurable physical evidence.

Ning Xu, Xiang Zheng, Fuqiang Zhong +4

Department of Computer Science and Technology, Tsinghua University, Beijing, China · ModelBest Inc., Beijing, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China +1

Feedback Control Autonomous Experimentation LLM Agent Reliability

Aug 5, 2026cs.LG

Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection

Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop. Many systems make these decisions by maximizing a myopic score such as expected information gain per unit cost or a learned plausibility score. We identify a structural limitation of this approach. Some actions are constructive: they acquire an epistemic capability (an instrument, assay, pipeline, simulator, or abstraction) whose value lies not in the information returned immediately but in the future actions it makes available. When the least-cost route to a confident answer requires a chain of such constructions, a planner that scores actions only by information obtainable within a bounded horizon cannot value the first construction: it yields no information within the horizon and is dominated by any measurement with positive information, however small. We formulate goal-directed discovery as a stochastic shortest-path problem in belief space in which constructive experiments change the downstream action graph, and prove that for every lookahead depth d there is an instance on which every myopic information-maximizing planner has an unbounded approximation ratio, and a related instance on which it never reaches the goal. The mechanism is a capability-indistinguishability lemma: within the horizon, acquiring a capability can be observationally indistinguishable from paying for a null action. This establishes capability gating as a reachability axis of difficulty distinct from curvature (submodularity) and information order (adaptivity gaps). We introduce CG-Plan, an incremental replanner with a capability-aware cost-to-go heuristic h = h_cap + h_exp. In a controlled testbed, the performance gap appears only under gating, persists for every fixed horizon, and arises when near-miss hypotheses come from a data-consistent proposer.

Ahmed Hassoon, Mark Dredze

Johns Hopkins University

Belief-Space Planning Cost-Aware Inference Autonomous Scientific Discovery Autonomous Experimentation

Aug 5, 2026cs.IR

From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents

Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions. Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings. We study \textbf{trajectory-to-evidence conversion}, asking what a completed research process has actually established. We introduce an evidence-grounded framework that couples bounded verification of consequential artifacts with post-execution claim qualification. A context-isolated generate--verify--repair process checks artifacts for evidence violations and missing downstream requirements before release. After execution, validity and attribution checks consolidate evidence across rounds, qualify intervention-level claims as actionable repairs, diagnostic guards, or withheld findings, and preserve admitted claims as auditable records with explicit provenance and applicability boundaries. A hybrid LLM-assisted controller subsequently applies, defers, or rejects records based on available target evidence. Record audits characterize which claims survive qualification, while downstream diagnostics identify affirmative applicability judgment as a bottleneck for the tested controller. Across paper-to-target adaptations, later rounds often improve on the first, while final rounds frequently underperform an earlier best, exposing non-monotonic trajectory evolution. Candidates produced through the complete workflow also yielded positive online lifts relative to deployed baselines.

Zijie Zhuang, Changxin Lao, Pengbo Xu +13

Kuaishou Technology, Beijing, China

Data Provenance Evidence-Grounded Reasoning Autonomous Experimentation Autonomous Research Agents Scientific Claim Verification

Aug 5, 2026cs.AI

A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing

Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation. Traditional tuning requires experts to repeatedly design strategies, configure experiments, analyze results, and adjust parameters, making the process labor-intensive and time-consuming. Meanwhile, valuable knowledge from historical experiments is often fragmented, making systematic reuse difficult through manual expert effort alone. Existing RAG agents partially alleviate this burden by retrieving prior strategies, but typically organize experience in a flat manner, overlooking the hierarchical relationships among business scenarios, recommendation stages, optimization objectives, and experimental contexts. This often results in mismatched retrieval and limited cross-scenario transfer, while preventing agents from continuously refining strategies and parameters through sequential A/B feedback. % To address these limitations, we propose A/B Agent, a closed-loop A/B agent for industrial recommendation strategy optimization. The framework comprises three tightly coupled core components: Historical Strategy Knowledge Organization, Autonomous Target-Aware Strategy Generation, and Experiment-Guided Strategy Self-Evolution. It organizes historical strategies into a hierarchical experience tree, retrieves transferable evidence through multi-path Tree-RAG to generate executable strategies, and continuously analyzes online A/B feedback to guide autonomous tuning and update the experience tree for self-evolution. Extensive offline and online evaluations demonstrate its effectiveness, including a 4.829% improvement in GMV in a real-world short-video e-commerce recommendation system while maintaining positive gains across all guardrail metrics.

Zhuohang Jiang, Yuxin Chen, Yongsen Pan +6

The Hong Kong Polytechnic University Hong Kong SAR, China · Kuaishou Technology Beijing, China · Southwest Jiaotong University Chengdu, SiChuan, China

Retrieval-Augmented Generation Recommender Systems Autonomous Experimentation Self-Evolving Agents

Aug 4, 2026cs.AI

Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Design

AI for Research (AI4Research) leverages AI to automate and improve scientific workflows. While experimental design is a critical stage of the research process, prior work has focused primarily on code implementation and execution, overlooking the importance of this stage, and no benchmark exists to evaluate AI's ability to conduct systematic experiment design. To bridge this gap, we propose SCOPE, a Scientific COmprehensive Planning Evaluation Benchmark constructed from 300 high-quality latest papers across 19 research domains from top-tier venues (e.g., ICML, NeurIPS, and ICLR),evaluating LLMs on two dimensions: High-Level planning completeness (main, ablation, and analysis experiments) and Low-Level configuration accuracy and rationality (datasets, baselines, and metrics). Benchmarking reveals three findings: (1) most LLMs cannot directly design high-quality experiments; (2) all LLMs exhibit a performance bottleneck in low-level configuration; and (3) search mode does not improve design quality. Furthermore, to address these challenges, we propose OptED, a novel agentic workflow to optimize LLM-based experimental design, that enhances LLM-based experimental planning through stage isolation, tool augmentation, and rule-based constraints, effectively alleviating the configuration bottleneck.

Zejun Liu, Jian Wu, Ru Peng +4

Westlake University · Zhejiang University · Nanjing University of Science and Technology +1

AI for Science Benchmark Design AI Agent Benchmarks Large Language Model-Guided Scientific Discovery Autonomous Experimentation

Aug 3, 2026cs.AI

Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering

Long-horizon autonomous research tasks such as machine learning engineering require systems to make interdependent decisions under a limited budget. Existing LLM-based agents typically organize candidate-solution improvement through tree, graph, or chain structures, meaning that the search process determines how information is acquired and managed. We call this design solution-centric search and propose instead the information paradigm, in which an evolving information state represents the system's understanding of the task and guides solution improvement. We instantiate this paradigm in Iris, an inquiry-revision loop. For information acquisition, Iris generates local action plans from the current information state and uses epistemic actions to probe decision-critical unknowns without modifying the retained solution. For information management, Iris synthesizes observations across experiments into task knowledge composed of revisable claims with explicit scope and status. It updates this knowledge as new evidence arrives and constructs each decision context from raw evidence, structured summaries, or task knowledge at the required level of detail. On MLE-Bench, Iris attains a 64.9% any-medal rate under a 12-hour budget, the highest among compared systems. Across four tasks spanning harness engineering and model post-training, Iris also demonstrates cross-domain generalization.

Shaokang Fu, Yulong Tao, Linbo Jin +7

Alibaba Group · East China Normal University · Zhejiang University +2

Active Information Gathering Automated Machine Learning Autonomous Experimentation Autonomous Research Agents

Aug 2, 2026cs.AI

Agentic Stage-One Stellarator Optimization: Autonomous Multi-Objective Search for Finite-Beta Equilibria

Stage-one stellarator design searches a high-dimensional family of three-dimensional plasma boundaries and fixed-boundary MHD equilibria for configurations that jointly meet requirements on confinement, field-line topology, force balance, stability proxies, and geometry. These specifications do not provide a general constructive map to a validated finite-beta equilibrium. High-quality targets are commonly developed through iterative numerical optimization whose outcome depends on the initial configuration, active Fourier resolution, objective priorities, and local solver budget. Coordinating this process is computationally costly and expert-intensive, limiting both design throughput and the production of consistently evaluated data. We present a proof of concept for \emph{agentic} stage-one optimization. A bounded language-model agent diagnoses the current equilibrium and selects the next local optimization experiment, while deterministic DESC execution owns prescribed profiles and flux, symmetry, metric evaluation, solver validity, and acceptance. On a common-budget subset from an expanding finite-beta campaign, the number of gate-valid configurations increases from five inputs to nineteen outputs; median Boozer QS RMS decreases from

2.39\times10^{-4}

to

1.07\times10^{-4}

, and median maximum principal curvature decreases from

62.56

to

33.00\,\mathrm{m}^{-1}

. A complementary long route achieves a

9.10\times

QS reduction while repairing magnetic-well and curvature defects. The system also records every attempted local action as transition evidence, yielding 734 structured parent--action--outcome records in the reported experiments. These results show that agentic outer-loop control can sustain finite-beta, multi-objective search and turn repeated optimization into a scalable source of improved equilibria and reusable decision data.

Tingjia Zhang, Zhuoran Meng, Runlai Xu

AI Agents for Scientific Discovery Multi-Objective Optimization Autonomous Experimentation

Jul 31, 2026cs.AI

AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers

As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important. Existing benchmarks typically focus on static code generation, paper replication, or final answer correctness, but do not directly assess whether agents can interpret experimental evidence and use it to guide subsequent hyperparameter decisions. To address this gap, we introduce AgentHPOBench, a sequential benchmark comprising 30 executable machine learning tasks across seven research categories. Each task begins with a validated baseline run, after which an agent performs several sequential interventions. At each step, the agent observes the accumulated configurations, metrics, and logs before proposing the next valid configuration. We evaluate 12 widely used agents and conventional HPO baselines under a unified protocol. The results show that current agents exhibit measurable experimental optimization ability across domains, but still face clear limitations in sustained iterative refinement, complex log diagnosis, and consistent progress toward reported reference performance.

Tianyu Huai, Tingshuo Fan, Xinchi Chen +5

Shanghai Innovation Institute · East China Normal University · OpenMOSS +1

LLM Agent Evaluation AI Agent Benchmarks Autonomous Experimentation Hyperparameter Optimization

Jul 30, 2026cs.AI

An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop

Autonomous research loops driven by large language models can run machine-learning experiments at scale but tend to drift toward local refinements of whichever metric they optimise rather than testing the hypotheses that motivate the experiments. We address this structurally and present an AI Scientist for studying generalisation in quadruped robot navigation policies in simulation. Building on the autoresearch paradigm of Karpathy, our loop adds three components: an immutable experiment card that pairs each iteration's prediction with its outcome under a fixed schema, so a falsified hypothesis cannot be retconned; specialised subagents restricted to mechanical roles; and kkanbu, a preference oracle that holds the user's research taste as a typed knowledge graph and is the only component permitted to make subjective judgements. To isolate the oracle we run the identical loop twice across eleven research streams, with and without kkanbu. Neither arm drifts: both falsify roughly three quarters of their own hypotheses, and the best trained policy comes from the oracle-less arm. What the oracle changes is direction, not score: it alone explores test-time adaptation, it authored the winning designs where its arm led, and it carried lessons across streams that the other arm repeatedly re-derived. The scaffold keeps the loop honest; kkanbu decides where it looks.

Yiwen Zhang, Eloise Zeng, Jaeha Lee +1

Division of Physics, Mathematics and Astronomy, California Institute of Technology, Pasadena, CA 91125, U.S.A. · Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, CA 91125, U.S.A.

AI for Science Human-in-the-Loop AI Autonomous Experimentation Autonomous Research Agents

Jul 30, 2026cs.AI

Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch

Autoresearch improves machine-learning code by proposing changes, running full training jobs, and keeping changes that improve the metric. The efficiency of this loop depends not only on generating ideas, but also on the agent's ability to decide, before spending a training run, whether a proposed modification is likely to work. We study how the reliability of this pre-execution judgment changes over the course of an autoresearch trajectory. In public AutoSOTA logs (Li et al., 2026; Tsinghua FIB Lab, 2026), the fraction of helpful modifications falls from 70% in the first two iterations to 43% by iteration 6+. On 296 same-baseline modification pairs from 39 paper-derived AutoSOTA tasks, each containing one modification that improved the metric and one that did not, with measured outcomes hidden, an LLM judge given candidate rationales but no prior-attempt history reaches 79.5% accuracy on the pairs where strict consensus returns a verdict. On the full 366-pair benchmark, however, this ability weakens substantially late in the loop. As successful changes accumulate, selective accuracy - accuracy conditioned on a strict-consensus verdict - falls from 82.8% to 56.9%, while the judge remains willing to decide. We call this operational pattern the confidence cliff. Rehearse implements the loop change as a lightweight skill for autoresearch loops: propose several ideas, compare them before execution, run the most promising, and judge with a focused memory of similar past attempts and outcomes. This focused outcome memory raises late selective accuracy to 83.5%. Across 4,000 budgeted training runs over three loops, Rehearse improves the endpoint under the same training-run budget on nanochat, image classification, and time-series forecasting.

Jiazhen Ji, Shouhong Ding

Tencent

Language Model Self-Assessment Autonomous Experimentation Autonomous Research Agents LLM Agent Reliability Memory-Augmented Language Model Agents

Jul 29, 2026cond-mat.mtrl-sci

PUDA: An AI-Native Hardware Harness for Self-Driving Laboratories

Physical Unified Device Architecture (PUDA) is an AI-native hardware harness for self-driving laboratories (SDLs). Rather than building a human-centered graphical user interface (GUI) orchestration layer, PUDA creates a command-line runtime environment that lets agents observe, orient, decide, and act over experiments while hardware execution remains deterministic, atomic, and auditable. Headless by design, devices appear through discoverable command-line interfaces, JSON protocols are routed through a distributed messaging system, and command responses, data products, and reports are preserved as structured records. PUDA organizes protocols, runs, samples, measurements, and command logs into an AI-native data structure linked by run identifiers and timestamps, preserving provenance from submitted protocol through hardware response to resulting data products. PUDA separates scientific orchestration from physical operation and data telemetry: agents choose experiments, while PUDA executes validated commands and captures provenance-linked state, responses, and data. The contribution is not another optimizer, orchestrator, or recipe language. It is a practical execution and data environment for agentic SDLs; the broader physical AI implication is that PUDA provides an AI-native hardware harness for AI systems to interact with physical tools.

Zekun Ren, Hongzhao Tan, Jiaen Yee +1

Berkeley Education Alliance for Research in Singapore (BEARS) · School of Materials Science and Engineering, Nanyang Technological University (NTU)

Laboratory Automation Tool-Using Agents Autonomous Experimentation

Jul 27, 2026quant-ph

Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments

We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in diamond. NV centers are a widely used platform for quantum sensing, and the ability to control many measurements from a computer makes NV experiments a natural setting for autonomous workflows. We make two main contributions. First, we demonstrate an autonomous NV experiment workflow that combines persistent project records, quantitative calculation and data analysis tools, and deterministic experiment control. In one autonomous experiment, the agent selected a single NV center, calibrated its resonant frequency, measured

T_2^\ast

with Ramsey measurements, and added a Carr--Purcell--Meiboom--Gill (CPMG) measurement to check a weak feature that could be related to nearby

^{13}\mathrm{C}

. Second, we introduce two offline benchmarks that evaluate the agent's reasoning separately from laboratory execution. We evaluated both benchmarks with GPT-5.4, GPT-5.5, and GPT-5.6 Sol. In the Ramsey checkpoint benchmark, greater reasoning effort generally improved recognition of a residual resonance calibration offset. By contrast, in the pulsed optically detected magnetic resonance (pODMR) data evaluation benchmark, pulse sequence information alone produced more false positive resonance judgments at higher reasoning effort. Requiring an expected signal calculation kept false positive rates low across all three models and reasoning settings. The results suggest a clear division of labor for autonomous experiments. The agent forms scientific hypotheses and uses quantitative tools to evaluate data, while deterministic code controls the hardware and enforces safety constraints.

Takuya Isogawa, Ryotaro Okabe, Nutdech Phadetsuwannukun +2

Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA

AI Agent Benchmarks Laboratory Automation Agentic Reasoning Autonomous Experimentation Autonomous Research Agents

Jul 26, 2026cs.AI

Cost-Aware Recovery-Pathway Identification and Bayesian Optimization for Autonomous Materials Discovery

Autonomous laboratories automate experimental execution, but a campaign must also decide which recovery pathway merits optimization. We formulate this as a sequential decision problem with a discrete pathway-identification stage and a continuous within-pathway optimization stage under heterogeneous experimental costs. Our implementation, Coactive learning, combines a cost-sensitive Bayesian hypothesis-discrimination policy motivated by EC2 (Golovin et al., 2010) with Gaussian-process Bayesian optimization (Srinivas et al., 2010). Under explicitly stated assumptions, the expected spend of one fixed-budget campaign attempt is bounded by the expected pathway-identification cost plus the capped within-pathway optimization budget. We evaluate the method on synthetic benchmarks constrained by selected results reported for PNNL's CICERO selective-precipitation study (Ritchhart et al., 2026). The method performs comparably to an oracle-pathway Bayesian-optimization reference and to a strong split-plate baseline that discriminates pathways with its first plate, without receiving an oracle label for the correct pathway. It is given a candidate hypothesis space and a diagnostic likelihood model. On an NdFeB-inspired instance, it avoids the simulated penalty of a commit-first baseline that initially selects a plausible but inferior hydroxide pathway. This hypothetical wrong-first-commitment scenario is motivated by the hydroxide-oxalate performance contrast reported by CICERO. We characterize the sensitivity of these conclusions to the assumed cost model. The code and benchmark are open source.

Debajyoti Ray, Niranjan Srinivas

Coactive Science

Cost-Sensitive Learning Bayesian Optimization Bayesian Inference Materials Science Bayesian Experimental Design Autonomous Experimentation

Jul 26, 2026cs.RO

LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory

The deployment of embodied agents in self-driving laboratories could accelerate scientific discovery, yet their reliability is constrained by the irreversible and safety-critical nature of chemical experiments. Progress is further hindered by scarce failure data and the lack of fine-grained evaluation protocols. To address these challenges, we introduce LabRobFail, a failure-centric framework for learning and evaluating robotic failure analysis in chemical laboratories. LabRobFail-Sim injects controllable failures at the control, physics, and semantic levels, enabling the construction of LabRobFail-Data, which contains over 20,000 trajectories across 70+ task scenarios, five failure categories, and 11 fine-grained failure types. LabRobFail-Bench evaluates six capabilities spanning task understanding, failure detection, temporal localization, severity assessment, failure classification, and actionable correction. We further develop LabRobFail-VLM, a domain-specialized vision-language model that generates structured failure diagnoses and recovery instructions. On seen environments, it achieves 90.83% failure-detection accuracy and 77.21% temporal-localization accuracy, substantially outperforming general-purpose VLMs. When integrated as a real-time supervisor, it improves downstream task success rates by 4-16 percentage points, demonstrating the value of fine-grained failure understanding for closed-loop recovery and reliable laboratory autonomy. Our code and data are available at https://github.com/Su-ISE-2001/SciRobo

Haobo Wang, Baoli Sun, Anqi Zou +8

School of Software, Dalian University of Technology, Dalian, China · Shenzhen Loop Area Institute-Hong Kong Science and Technology Innovation Cooperation Zone, Shenzhen, China · School of Computer Science and Engineering, Harbin Institute of Technology, Harbin, China +3

Robot Failure Detection Robotics Laboratory Automation VLMs for Robotics Autonomous Experimentation

Jul 25, 2026cs.AI

Stress-testing large language model agents in a robotic chemistry laboratory

AI is evaluated through knowledge, reasoning and plan generation, yet scientific agency requires reliable physical action and adaptation to evidence. Here, we use a robotic chemistry laboratory as a physical-world testbed to make scientific agency measurable. Its 45 modular workstations exposed as machine-readable skills enabled 4,608 trials. Only 3.3% of trials produced expert-assessed executable workflows under laboratory constraints; even the best system achieved 28.1%. Long-horizon planning remained a challenge: only three executable workflows exceeded 30 operations, although the longest contained 44. Across five rounds, experimental feedback prompted local adjustments but no workflow-level replanning or analytical-method redesign. By making physical executability and evidence-driven replanning measurable, our study provides an evidence-based assessment of deployment readiness and a diagnostic framework to guide closed-loop improvements towards physically grounded autonomous research.

Lulu Guo, Yingkai Sun, Xiaobo Li +13

State Key Laboratory of Precision and Intelligent Chemistry, Hefei National Research Center for Physical Sciences at the Microscale, School of Chemistry and Materials Science, University of Science and Technology of China, Hefei, China · Center for Scientific Intelligence Innovation, Hefei, China · School of Chemistry, School of Computer Science, University of Birmingham, Birmingham, UK

AI Agent Reliability AI Agents for Scientific Discovery AI Agent Evaluation Robotics Laboratory Automation Autonomous Experimentation+1

Jul 22, 2026cs.RO

Scalable Low-Cost Laboratory Automation: A Digital Twin-Integrated Robotic Platform for Autonomous Liquid Handling (RAINBOT)

Laboratory automation accelerates discovery, yet its adoption is constrained by the high cost, proprietary design, and limited remote supervisability of commercial liquid-handling systems. This work presents RAINBOT\textsuperscript{TM}, a low-cost, openly reproducible liquid-handling robot built by converting a consumer-grade Cartesian 3D printer (Elegoo Neptune 4 Max). The printer extruder is replaced by a precision single-channel pipette actuated through the printer's own G-code-driven X--Y--Z gantry, with plunger and tip-eject motions effected by two compact linear actuators under Python control. To make experiments transparent and remotely supervisable, a browser-based digital twin is implemented to synchronise bidirectionally with the physical platform, mirroring kinematics and pipetting states in real time and exposing remote monitoring, intervention, and an emergency stop from any web browser. As a proof of concept, RAINBOT\textsuperscript{TM} performed sequential exchanges of differently coloured aqueous solutions while an integrated colour sensor quantified the resulting mixtures; measured red, yellow, and blue (RYB) responses agreed with expected mixing behaviour to within a mean absolute error of two percentage points, validating correct execution and real-time tracking. Closing the loop, the platform is coupled to the CEID\textsuperscript{TM} (Cooperative Explorer for Inverse Design) framework, which recasts experimentation from iterative manual guessing into a goal-directed inverse-design search while keeping a human in the loop. The complete hardware costs under US$1300, which is roughly an order of magnitude below entry-level commercial handlers, thereby establishing an accessible physical--virtual framework for self-driving laboratory automation.

Mohamed Rami Ayeche, Souhil Sid, Ahyen Mostofa +3

Acceleration Consortium, University of Toronto, Toronto, Canada. · AISCIA Informatics, Qatar Science and Technology Park, Doha, Qatar · Hamad Bin Khalifa University (HBKU), Education City, Doha, Qatar.

Laboratory Automation Robotic Manipulation Autonomous Experimentation

Jul 13, 2026cs.DC

Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap

One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The field has since moved faster than anticipated. Multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain foundation models have raised the capability ceiling, and the Genesis Mission has placed autonomous experimentation at the center of U.S. federal science strategy, with industry emerging as a primary actor. Progress has met a sobering counter-current, including a corrected flagship discovery result, benchmarks showing that agents which rival experts on closed-ended questions still complete only a fraction of open-ended research, and fabricated citations surfacing at leading venues. We read this as the defining tension of the field. Producing a candidate discovery is no longer the hard part, but verifying it is, and this asymmetry now limits autonomous science more than raw model capability. We update the roadmap around seven dimensions, revisiting the original five and elevating two former cross-cutting concerns, trust, verification, and reproducibility, and safety, security, and governance, to first-class status. We assess the original milestones (M1 through M14) as achieved, partially achieved, reframed, or open, add four new milestones (M15 through M18), and scope the path forward to a two-year horizon. The first year concentrates on interfaces, protocol adoption, and the scaffolding of verification, and the second targets federation, zero-trust coordination, and governance. Throughout, we position the grassroots network as the interoperability fabric that lets national programs, international initiatives, and commercial platforms connect rather than re-silo.

Rafael Ferreira da Silva, Milad Abolhasani, Peter Beaucage +25

Oak Ridge National Laboratory

Autonomous Scientific Discovery AI Agent Governance Scientific Reproducibility Autonomous Experimentation

Jul 7, 2026cond-mat.mtrl-sci

From Closed-Loop Optimization to Open Decision Making: Coupled Digital Twins for Predictive and Autonomous Microscopy

Automated experimentation is moving from closed-loop optimization toward open decision-making, where human or AI planners must forecast the consequences of candidate actions before executing them. Such forecasts require a model of both sides of the experiment: how the sample is likely to respond and what the instrument is likely to detect. We therefore introduce a coupled digital-twin framework that separates these roles and then links them. In this framework, the sample twin encodes material state inferred from prior knowledge and measurements till the moment. The instrument twin captures signal formation, feedback dynamics, and operating constraints based on prior knowledge. When coupled, the two twins estimate expected outcomes, uncertainty, and risk for candidate microscope operations. For amplitude-modulation scanning probe microscopy, we realize this framework with a physics-informed encoder of force-distance curves, a deterministic scanner model of cantilever and feedback dynamics, and sparse learned residual corrections. The encoder first recovers scanner-driving descriptors with sub-nanometer accuracy. The calibrated scanner then reproduces typical traces within a few nanometers and identifies operating-point noise amplification as the main source of mismatch. Supplementary phase analysis localizes residual error to the phase channel, which clarifies where added physics is needed. Together, these results establish coupled sample and instrument twins as a practical foundation for predictive microscope operation and autonomous experimental planning.

Yu Liu, Boris Slautin, Ian Mercer +2

Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee, 37996, USA · Materials Science and Engineering Department, Materials Research Institute, the Pennsylvania State University, University Park, Pennsylvania, 16802, USA

Digital Twins Autonomous Experimentation

Jul 5, 2026cs.AI

Compressing the Validation Bottleneck: An Agentic Self-Driving Lab for Scientific Discovery

Agentic AI-for-Science can automate ideation, planning, and analysis, but final validation still depends on real experiments. A self-driving lab (SDL) can execute those experiments, yet the loop still has bottlenecks: the agent may spend too many rounds on low-value experiments, or each round may require a high-cost experiment. We target these two physical bottlenecks with one agent. First, a prior-aware agentic DOE loop uses domain knowledge and past results to propose feasible and informative next experiments, reducing trials-to-target. Second, a cost-aware surrogate agent predicts high-cost, high-resolution measurements from low-cost, low-resolution measurements. It chooses between a high- and a low-cost measurement based on the predicted uncertainty. We examine these directions in the biology and materials domains, respectively. Together, under a single agent, these components aim to accelerate the SDL loop by reducing both the number of loops and the cost per experiment.

Kyunghoon Hur, Chihun Lee

AX Research Division, Korea Electronics Technology Institute, Republic of Korea · Material Data Division, Korea Institute of Materials Science, Republic of Korea

AI for Science Multifidelity Modeling Laboratory Automation Autonomous Experimentation

Jul 1, 2026cs.AI

Optimal Resource Utilization for Autonomous Laboratory Orchestrators

In autonomous laboratories, AI agents suggest the next batch of experiments to do. However, planning and executing those tasks taking full advantage of the available resources is a completely different question. This can be challenging when dealing with real-world hardware constraints, especially so when there are multiple instruments with different capacities and throughputs. Here we demonstrate a 2-step method to address resource utilization for our autonomous platform for metal-organic framework synthesis. First, we use constraint programming to find optimal schedules. This finds schedules that minimizes the total time while still satisfying the limitations and capacities of the hardware. Secondly, we use a system of status dependencies for each task, which allows for the robust execution of the optimal schedules.

Austin McDannald, Julia Tisaranni, Howie Joress

Material Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA

Laboratory Automation Scientific Workflow Automation Autonomous Experimentation

Jun 30, 2026cs.AI

A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols

Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conversion as an experimental automation problem. The framework spans 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols, wet-lab expert rubrics, device-level validity gates and real experimental tests. ProtoPilot incorporates layer-wise verifiability, multi-agent orchestration and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code and revise workflows from wet-lab feedback. It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5% and an Opentrons pass rate of 88.24%, compared with 32.35% for OpenTrons-AI. Wet-lab validation produced interpretable readouts, Sanger-confirmed products and feedback-corrected PCA-assembled DNA targets, establishing a verifiable route to autonomous experimentation. Together, these results show that the evaluation framework captures execution-relevant requirements for autonomous wet-lab automation, and that ProtoPilot can meet them by converting protocol and code generation into validated execution and feedback-guided revision.

Yankai Jiang, Weiting Tang, Haoran Sun +11

1Shanghai Artificial Intelligence Laboratory, Shanghai, China · 2Genoria AI, Shenzhen, China

Scientific Code Generation Laboratory Automation Scientific Workflow Automation Autonomous Experimentation Self-Evolving Agents

Jun 30, 2026cs.AI

FARS: A Fully Automated Research System Deployed at Scale

Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few pre-defined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes. We evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

Qiong Tang, Tianxiang Sun, Xiangkun Hu +54

AI Agent Evaluation Autonomous Scientific Discovery Large Language Model-Guided Scientific Discovery Autonomous Experimentation Autonomous Research Agents

Jun 30, 2026cs.AI

One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution

Autonomous research agents can now draft hypotheses, write code, run experiments, and produce papers, but they remain brittle when experiments fail. Under the prevailing paradigm, failure recovery is usually delegated to a single free-form reflection: a rich trajectory of metrics, logs, and design choices is compressed into one verbal critique, which often leads either to localized trial-and-error or to hard pivots that discard useful context. We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter, to tackle this failure-recovery bottleneck. Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis. By analyzing dynamic trajectory features, MHFA systematically generates multiple evidence-grounded explanations for a failure, independently evaluates their severity, and deterministically routes the verified root cause to the correct intervention level (hypothesis, experimental design, or implementation). To guarantee scientific honesty, SAGE further employs a grounded reporting mechanism that explicitly constrains drafted results to actual measured values, redacting hallucinated numbers. On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a reflection baseline, improves artifact quality from 5.00 to 6.75/10, and blindly outscores AI-Scientist-v2 (52.0 vs. 48.2), with gains concentrated in code development and execution. While fully autonomous scientific writing and generating conference-ready papers remain notoriously difficult open problems for the entire field, SAGE successfully produces significantly more reliable and higher-quality scientific artifacts. Ultimately, by coupling structured recovery with explicit grounding constraints, SAGE significantly outperforms monolithic reflection paradigms, establishing a highly trustworthy foundation for future autonomous research.

Jie Ma, Binfei Chu, Jie Gao +6

Xiamen University · Hello Inc. · Xiaohongshu Inc.

Agent Failure Analysis LLM Self-Correction Autonomous Experimentation Autonomous Research Agents

Jun 28, 2026cs.LG

STEMGym: Benchmarking Sequential Decision-Making under Dose Budgets in Autonomous Electron Microscopy

A central premise of autonomous scientific imaging is that smarter navigation, whether Bayesian, RL-based, or otherwise adaptive, is the principal lever for sample-efficient acquisition. We present evidence to the contrary in scanning transmission electron microscopy (STEM), an atomic-resolution imaging modality whose every measurement deposits damaging electron dose. We introduce STEMGym, an open-source Gymnasium benchmark of 15 physics-simulated STEM worlds spanning five materials, three difficulty levels, and four characterisation tasks, scored by the Dose-Efficiency Curve area (DEC-AUC), a single scalar capturing the information-vs-dose Pareto frontier. Across 33 agent configurations under realistic dose budgets, the dominant determinant of dose efficiency is the analyst (perception) pipeline, not the navigator: pairing a trained CNN analyst with naïve raster scanning raises DEC-AUC by 5.5x over a CNN-free raster baseline (0.287 vs.\ 0.052), while substituting Bayesian or adaptive finite-state-machine navigation for raster yields no statistically significant further gain. Production-tier vision-language models further underperform task-specific CNNs by {\sim}13x on crystallographic defect analysis. By decoupling perception, navigation, and planning under a unified dose budget, STEMGym reframes where ML effort should be invested in autonomous electron microscopy and provides the measurement infrastructure to test it.

Can Polat, Erchin Serpedin, Mustafa Kurban +1

Dept. of Electrical & Computer Eng. Texas A&M Univ. College Station, TX, USA · Dept. of Prosthetics & Orthotics College of Science & Eng. Ankara Univ., Ankara, Turkey · Hamad Bin Khalifa Univ. and Texas A&M Univ. at Qatar Doha, Qatar

Autonomous Experimentation Microscopy Image Analysis

Jun 25, 2026cs.AI

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the agents themselves -- making the system not merely automated, but self-improving.

Changxin Lao, Fei Pan, Guozhuang Ma +59

Software Engineering Agents Multi-Agent Collaboration Recommender Systems Self-Improving Agents Autonomous Experimentation

Jun 25, 2026cs.AI

Socratic agents for autonomous scientific discovery in high-dimensional physical systems

The automation of scientific discovery has reached an inflection point. While AI systems now operate instruments, optimize parameters and generate hypotheses, most remain procedural: they execute workflows fixed by human designers. True autonomous science demands epistemic autonomy--the capacity to construct, challenge and revise physical explanations in response to evidence. Here we introduce AHOIS, a multi-agent AI scientist that embeds Socratic midwifery into closed-loop experimentation. A physics-critic agent interrogates hypotheses through causal questioning, constraint checking, counterexample generation and falsification-criteria formulation. We evaluate AHOIS on a real multimode-fibre optical platform, a high-dimensional system with complex wave transformations, indirect detection, environmental drift and multi-modal acquisition. Without prior encoding schemes, classifiers or speckle models, the system autonomously proposed and validated a random-interference encoding hypothesis, discovered task-adaptive sparse-measurement strategies, diagnosed distinct failure modes (encoding instability, fluorescence contamination and detector noise) and translated a published imaging protocol into an executable workflow on a non-original configuration. The discovered encoding yielded 16x16 measurements with effective rank 56.9 and classification accuracies of 76.97% on MNIST and 83.17% on Fashion-MNIST. Ablations show that Socratic interrogation improves physical consistency, hypothesis completeness, uncertainty calibration and experimental-plan validity. These results establish a route from workflow automation towards evidence-grounded, self-correcting autonomous discovery in complex physical environments.

Xianrui Zeng, Pengfei Liu, Yirui Zang +5

Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, China. · Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, 201800, China. · Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, 200433, China. +1

Scientific Hypothesis Generation Autonomous Scientific Discovery Autonomous Experimentation

Jun 24, 2026cs.AI

auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation

AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is a major bottleneck in this pipeline, however. Psychology, and computational cognitive science in particular, is well-positioned to benefit from AI experimentation because theories are often represented as code and crowdsourcing platforms enable programmatic human data collection at scale. Here, we apply automated discovery techniques to the project of generating theories in computational cognitive science, with an agent-based system collecting human data independently through crowdsourced survey experiments. As a testbed, we use a classic case study from cognitive psychology: judging which sequences of coin flips seem subjectively more random. Our system, auto-psych, uses nested agent-based discovery loops to generate explanatory theories of human behavior. The inner loop conjectures, fits, and critiques probabilistic cognitive models; the outer loop designs experiments to test these models, launches them online, and analyzes the data. This system can quickly and reliably recover ground-truth theories from synthetic data via systematic experimentation, but the nested structure is critical to model performance. Further, in three independent sequences of human experiments, the system finds theories that fit the data better than theories generated from the scientific literature. This work thus demonstrates the feasibility of automated data collection and theory discovery in computational cognitive science.

Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft +4

Department of Psychology, Stanford University · Department of Computer Science, Stanford University

Computational Cognitive Modeling Autonomous Scientific Discovery Autonomous Experimentation

Jun 24, 2026q-bio.NC

Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist

Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approach is yet to be applied in the field of cognitive science, where the central bottleneck is theory-building: the creative step of turning the accumulated failures of existing models into better ones. Theory generation has remained manual even as data collection, modeling, and experiment design have been automated. We present the Automated Cognitive Scientist (AutoCog), a fully autonomous agentic-AI system that closes this loop. Large-language-model agents advocate competing theories, each expressed as an executable cognitive model, design experiments that best discriminate them, collect behavioral data from participants recruited online, score theories against collected data based on their generative performance, diagnose why they fail, and synthesize a better successor. Repeating this cycle allows them to search the space of theories, models, and experiments. In the domain of decision-making, AutoCog recovered known decision-making strategies from simulated behavior, including unconventional ones, showing that its discoveries are ultimately driven by the data rather than strictly bound by the priors of the underlying language models. When run with human participants, it produced theories that outperformed the established theories it was seeded with and generalized to held-out studies in two different experimental settings. It also surfaced a novel theory of multi-cue decision-making in which choices show diminishing sensitivity to feature values. The distinctive predictions of this theory were confirmed in a preregistered study with new participants. AutoCog demonstrates how an automated discovery system can be used to turn cognitive theory-building into an explicit, executable, and cumulative science.

Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby +5

Princeton AI Lab, Princeton University

Computational Cognitive Modeling Autonomous Scientific Discovery Large Language Model-Guided Scientific Discovery Autonomous Experimentation

Jun 23, 2026cs.SE

Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy

Large language models are making research production scalable, shifting the bottleneck from producing artifacts to judging claims. We present \textsc{Agon}, a research orchestrator that validates what can be checked inside the workflow and leaves the remaining judgments to human scientists. \textsc{Agon} is built on six design principles: Prompt Economy, Future-Facing, Minimal Prompts, OmniDisciplinary, Massive Parallelism, and Zero-Code. We ran \textsc{Agon} across domains for 444 iterations of Prompt Economy loops, using only small starting topics and no human-written experimental code. These deployments demonstrate scalability while exposing new classes of failure. We organize these failures into a taxonomy along severity, fixability, visibility, and capability locus. The taxonomy separates failures the loops can see and fix from those that require human judgment. Together, these results show that \textsc{Agon} is pushing research toward a new paradigm: machine scales, human steers.

Youran Sun, Xingyu Ren, Chugang Yi +4

University of Maryland, College Park, College Park, MD, USA · The Chinese University of Hong Kong, Hong Kong, China · Stanford University, Stanford, CA, USA

AI Agents for Scientific Discovery Human-in-the-Loop AI Autonomous Experimentation Autonomous Research Agents LLM Agent Reliability

Jun 18, 2026cs.RO

Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems

Spacecraft guidance, navigation, and control functions are increasingly realized as learned policies distilled from expert solvers. Developing such a policy is itself a research process: an investigator selects an architecture and hyperparameters, runs experiments, and must determine whether an apparent improvement is genuine or merely seed noise. This paper presents AutoResearch, a framework in which a large language model autonomously drives that loop for aerospace control problems, coupled with a credibility layer, built into the loop, that certifies each reported result against the problem's own measured seed noise. The language model serves only as the offline research agent that develops the control policy; the trained policy it produces is then deployed onboard the spacecraft, while the model itself never operates the vehicle. At each iteration the agent reads a plain-language problem description and the run history, proposes a single edit to the training script, executes it, and logs the outcome. No reported result is credited until it passes the same three checks: measured per-problem seed noise, reseeded verification of the best configuration, and leave-one-out pruning of the agent's edits. The same loop is applied, unchanged, to two aerospace control problems: a Clohessy-Wiltshire relative rendezvous and a safety-constrained collision-avoidance docking past a keep-out zone, each calibrated against a known optimal control benchmark. In both, the audited policy clears the measured seed noise by many standard deviations; an undirected search over the same parameters does not. On the docking problem the gap becomes categorical: undirected search yields no feasible policy, while the learned policy stays outside the keep-out zone on every seed.

Amit Jain, Richard Linares

Massachusetts Institute of Technology, Cambridge, MA, 02139

Autonomous Experimentation Autonomous Research Agents

Jun 18, 2026cs.RO

Dual-Agent Framework for Cross-Model Verified Translation of Natural-Language Protocols into Robotic Laboratory Platform

Biological experiment protocols are written in natural language, whereas automation systems rely on predefined control commands, creating a semantic gap that limits autonomous execution. Microplate-based automatic experiments are particularly challenging due to the need to simultaneously control well mapping, sample-reagent combinations, replicate placement, and parallel dispensing. This study proposes an agent-based protocol translation framework that converts natural-language microplate-based protocols into executable control commands for a robotic laboratory platform. A Parser Agent formalizes the natural-language protocol into a structured representation, and a rule-based mapping engine deterministically incorporates the operational constraints of the robotic laboratory platform to generate device-level control commands. A heterogeneous LLM Validation Agent verifies completeness, parameter accuracy, and execution order, and triggers a self-correction loop with structured feedback when errors are detected. A sweep involving 7 Parsers and 3 Validators on randomly selected ELISA protocols evaluates how model scale and Validator type affect translation accuracy and pass rates under cross-model verification. The accuracy-latency trade-off is further verified by comparing the rule-based mapping of the proposed framework with LLM end-to-end direct mapping. Finally, Bradford assay-based protein quantification using a microplate was demonstrated on a robotic laboratory platform, validating end-to-end autonomous execution from natural-language protocols to real-world experiments. The proposed framework provides a flexible approach to narrowing the semantic gap between natural-language protocols and microplate-based self-driving laboratories.

Hyeonna Choi, Jung Yup Kim, Hyuneui Lim +1

Department of Bionic Machinery, Research Institute of AI Robot, Korea Institute of Machinery & Materials, 156, Gajeongbuk-ro, Yuseong-gu, Daejeon 34103, South Korea · 156, Gajeongbuk-ro, Yuseong-gu, Daejeon 34103, South Korea · Department of Nano-devices & displays, Nano-convergence Manufacturing Research Division, Korea Institute of Machinery & Materials, 156, Gajeongbuk-ro, Yuseong-gu, Daejeon 34103, South Korea

LLM Agent Orchestration Laboratory Automation Scientific Workflow Automation Autonomous Experimentation LLM Agent Reliability

Jun 18, 2026physics.chem-ph

Empowering Polymeric Materials Discovery by Artificial Intelligence

Polymeric materials underpin modern technologies spanning energy storage, microelectronics, healthcare and sustainable manufacturing. Yet their rational design remains exceptionally challenging because material performance emerges from complex interactions among molecular composition, chain architecture, processing history and hierarchical structural evolution across multiple length and time scales. Consequently, polymer research has long relied on labor-intensive experimentation and fragmented modeling approaches, limiting both mechanistic understanding and innovation efficiency. Recent advances in data infrastructure, machine learning, large artificial intelligence (AI) models and laboratory automation are beginning to reshape this landscape. Rather than functioning as isolated tools, polymer databases, predictive models, AI agents and automated laboratories are increasingly converging into interconnected discovery ecosystems. As a result, the central challenge is shifting from improving predictive accuracy alone to enabling reliable decision-making, adaptive learning and seamless integration across computation, experimentation and scientific reasoning. We argue that polymer science is entering an era of autonomous discovery, in which data, simulation, reasoning and experimentation operate within self-improving feedback loops that continuously generate hypotheses, design materials, execute experiments and refine predictive models. By unifying molecular design, process optimization, experimental validation and industrial translation, such autonomous ecosystems establish a more predictive, reproducible and scalable paradigm for polymer innovation, fundamentally transforming how polymer research is conducted.

Chenyao Ma, Linda Zhang, Yuheng Chen +29

Suzhou MatSource Technology Co., Ltd., Suzhou 215000, Jiangsu, China. · Advanced Institute for Materials Research (WPI-AIMR), Tohoku University, Sendai 980-8577, Japan. · Frontier Research Institute for Interdisciplinary Sciences (FRIS), Tohoku University, Sendai, 980-8577, Japan. +11

AI Agents for Scientific Discovery Materials Science Autonomous Scientific Discovery Autonomous Experimentation

Jun 14, 2026cond-mat.mtrl-sci

NIMO: A Software Platform for Closed-Loop Materials Exploration with Diverse AI Algorithms

Self-driving laboratories (SDLs), where artificial intelligence proposes subsequent experiments and robotic systems execute them, are rapidly becoming the vanguard of materials discovery. A critical bottleneck, however, lies in seamlessly bridging diverse AI algorithms tailored for specific exploration goals with the heterogeneous robotic hardware found across different laboratories. Here, we present NIMO, an open-source software platform designed to dissolve this barrier through three core paradigms: a modular AI-robot decoupling mediated via simple CSV file exchange, a discrete candidate-pool architecture that seamlessly absorbs domain knowledge, and a unified Python interface pre-loaded with twelve distinct AI algorithms. In this Perspective, we review the operational principles of each algorithm alongside six diverse SDL implementations driven by NIMO, covering electrolyte discovery, organic synthesis, thin-film exploration, fuel-cell process informatics, coffee-ring phase exploration, and legacy liquid-handling automation. One of these also demonstrates NIMO's seamless interoperability with the IvoryOS orchestration framework. To democratize autonomous science, we also introduce a no-code desktop application that enables intuitive, human-in-the-loop exploration for non-programmers. NIMO is freely available at https://github.com/NIMS-DA/nimo, offering a versatile, plug-and-play foundation to accelerate autonomous materials exploration across diverse experimental landscapes.

Ryo Tamura, Naruki Yoshikawa, Koji Tsuda +1

Center for Basic Research on Materials, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan · Graduate School of Frontier Sciences, The University of Tokyo, 5-1-5 Kashiwa-no-ha, Kashiwa, Chiba 277-8561, Japan · Center for Green Research on Energy and Environmental Materials, National Institute for Material Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan

Materials Science Scientific Workflow Automation Autonomous Experimentation

Jun 12, 2026cs.LG

Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation

The autoresearch pattern enables autonomous experimentation by having a large language model (LLM) iteratively modify code to optimize a target metric. Its stateless design, however, reconstructs experimental context from scratch at every iteration, incurring

O(n)

token cost per iteration and

O(n^{2})

total. This work reformulates the pattern as a stateful ReAct agent using LangGraph, where typed persistent state carries experimental history across iterations via a tool-calling interface. Two benchmarks are evaluated: hyperparameter tuning (15 iterations, small per-iteration observations) and code performance optimization (40 iterations, large per-iteration observations containing full source code and benchmark results). On hyperparameter tuning, the stateful agent consumes 90% fewer tokens (2{,}492 vs.\ 24{,}465). On code optimization, the stateful agent consumes 52% fewer tokens (627K vs.\ 1{,}275K) while achieving comparable optimization quality on both tasks. The token reduction is structural: the stateless agent re-reads the full history at

O(n)

cost per iteration, while the stateful agent operates within a fixed-size conversation window at

O(1)

cost. This paper describes the architecture in sufficient detail for practitioners to implement a stateful autoresearch agent for their own workflows.

Faramarz Jabbarvaziri

Large Language Model-Guided Optimization LLM Agent Workflow Optimization LLM Agents State Tracking Autonomous Experimentation Memory-Augmented Language Model Agents