Autonomous Scientific Discovery

Overview

The field studies how AI can move beyond answering questions to uncovering patterns, mechanisms, equations, and useful experiments across mathematics, physics, biology, and materials science. Approaches include symbolic regression and sparse equation identification, active learning and Bayesian experiment selection, and LLM-based agents that coordinate coding, simulation, literature review, or laboratory work. Evaluation increasingly uses executable benchmarks, held-out data, formal proofs, and experimental validation to check both results and the evidence behind them. Systems can handle well-specified workflows, but open-ended insight, reliable mechanism claims, identifiability, and reproducibility remain difficult, motivating stronger verification and human oversight.

Latest papers

137 papers12 papers in the last four weeks, down 40% on the four weeks before. 0.1% of all new papers.

Nov 16, 2026

Inventa: Decentralized Self-Improving Agents for Autonomous Scientific Discovery

Large language model (LLM) agents can generate research ideas and improve scientific discovery through iterative experimentation. However, increasing the number of agents or iterations does not automatically translate to producing more diverse or feasible ideas. Agents may converge on similar candidates, propagate unsupported claims through shared memory components and repeatedly apply search strategies that no longer yield any improvements. We introduce Inventa, a framework for automated scientific discovery that employs autonomous research units and verified shared knowledge. Each unit creates a lineage of candidate ideas using a mutator agent. A local orchestrator agent periodically adapts the mutator's harness. When progress stalls, the orchestrator agent replaces its model or restarts the idea evolution process. Verifiers evaluate each candidate idea and record verified improvements, useful components and constraint violations in a shared knowledge, the only channel between units. We evaluate Inventa on five benchmarks spanning the research cycle, covering retrieval (ScholarCatalyst), ideation (IdeaBench), proposal writing (IdeaScientist), and scientific law discovery (EurekaBench, SciLaws-Bench). It leads all five, achieving 73.6% on EurekaBench versus 56.2% for CORAL. On IdeaBench, it discovers 26.0 novel ideas per paper, compared with 18.6 for ResearchAgent, with 82% fewer model calls.
Nov 15, 2026

Asking the right question is key to AI discovery in a chain of hypotheses

Artificial intelligence (AI) scientists pursue discovery through a chain of hypotheses, fitting candidate models to existing observations and often choosing experiments where those models disagree most. Yet when early data miss a narrow feature, model selection favors simple curves that agree across the unmea- sured gap, so disagreement-guided search has no reason to look where the new phenomenon lies. When we tested two frontier AI scientists, Claude Sonnet 5.5 and GPT-6.1-Sol, across 32 closed-loop trials with a narrow peak omitted from the starting data, both sampled inside the peak region less often than random search. Surprisingly, the agent that followed model disagreement more closely missed the peak in all 32 trials, whereas discovery succeeded when experiments probed the unmeasured gap early and followed up across the anomaly. Asking the right question, rather than testing only where current models disagree, is therefore key to AI discovery in a chain of hypotheses.
Nov 12, 2026

Vibe synthesis: hierarchical agentic decision-making for intent-driven multistep molecule synthesis

The ability to construct complex molecules underpins advances in medicine and the molecular sciences. Yet long-horizon multistep synthesis requires decisions to be revised as evidence accumulates across chemically dependent operations, a capability not readily supported by artificial-intelligence tools and automated platforms organized around predefined tasks and hard-coded workflows. Here we propose and demonstrate a vibe synthesis system (VibeSyn), an intent-driven architecture in which hierarchical agents translate chemist-defined molecular objectives and accumulating evidence into adaptive decisions executed through computational tools and laboratory automation. We evaluate VibeSyn in three demonstrations of increasing scope and autonomy, progressing from evidence-grounded experimental decisions to adaptive execution of a ten-step total synthesis of catharanthine and structure-to-compound synthesis of cyclic peptides containing unnatural amino acids (uAAs). Across the long-horizon campaigns, active human input and simple confirmation account for less than 7.5% and 5.2%, respectively, of recorded workflow actions and outcomes. VibeSyn points towards a future in which chemists define synthetic intent and agent-directed laboratories autonomously navigate the evolving experimental trajectory required to deliver the target compound.
Nov 10, 2026

Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim hh only against its complement ¬h\neg h. When evidence rejects hh, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast set, a scientific question paired with mutually exclusive and collectively exhaustive competing explanations. Each experiment is scored by how its evidence redistributes belief across the set, and the question is resolved when belief concentrates on one explanation. Because contrast sets change only the unit an agent proposes and scores, an existing agent can use them to re-evaluate evidence it has already collected or to guide its search. Across six domains, 89%89\% of the pointwise candidates with the largest belief shifts are rejections. On the same evidence, contrast sets resolve 73%73\% of these candidates to a specific alternative. When contrast sets guide search, the agent resolves 67%67\% more questions than pointwise surprisal under the same experiment budget. In a blinded study, 3838 human experts chose the same explanation on 78%78\% of resolved questions and on 82%82\% of questions where the pointwise agent rejected its hypothesis and stopped. Together, these results support explicit competing explanations as a way for discovery agents to resolve more scientific questions from the same evidence and validation budget.
Nov 10, 2026

Adaptive catalyst discovery emerges from composable scientific intelligence

Catalysis underpins chemical manufacturing, yet knowledge for catalyst design remains dispersed across experimental observations, computational data and catalysis subdisciplines. To overcome this challenge, we present Composable Catalytic Intelligence (CatAI), a physics-grounded modular AI framework that learns 1.8 million structure-property relations and organizes them into 30 physicochemical encoders. This reusable intermediate layer enables task-specific models to guide catalyst discovery for targeted reactions and objectives. Across benchmark tasks, CatAI achieves a 7.8% lower task-averaged prediction error than the next-best models. In experimental validation, CatAI identified a new confined-passable pocket catalyst applicable in industrial homogeneous polymer synthesis with 9 times the activity of the commercial benchmark. In parallel, it guided autonomous closed-loop optimization of a highly active Cu-based geminal-atom photocatalyst for C-O coupling reactions surpassing the traditional Ni-based systems. This approach connects property-level data to catalytic objectives, supporting physicochemical knowledge reuse across mechanistically distinct systems through computational screening and iterative model-experiment feedback.
Nov 9, 2026

Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2. It also performs well on two external scientific ideation benchmarks. Five expert-guided collaborations further connect its proposals to experimental and computational validation across chemistry, materials science, and engineering. In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. These results support metacognitive regulation as an approach to scientific ideation and its progression toward practical validation.
Nov 9, 2026

SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery

We propose SciMARS, a framework for recursive task-local adaptation of multi-agent harnesses in closed-loop scientific discovery. Multi-agent systems coordinate analysis, experimental design, and verification as scientific evidence evolves. However, two problems limit their effectiveness: (i) without shared memory, agents lose observations and repeat work; (ii) fixed role procedures, handoffs, and memory policies perpetuate mistakes despite retained evidence. We address these problems with a shared evidence graph and separate component editors. SciMARS adapts roles and coordination; SciMARS + Memory adds a third editor for how agents record, retrieve, and receive evidence. Candidate probes guide composition and selection of the next harness. We evaluate scientific discovery through experimental-data replay and a digital twin. SciMARS + Memory resolves 12/18 GPT-6-Astra and 2/18 GLM-5.3 attempts on Autonomous Science Bench, compared with 8/18 and 1/18 for the base multi-agent team. On ScienceAgentBench and AppWorld, it solves 14/38 and 11/20 tasks, compared with 11/38 and 5/20 for the base team. These results support combining shared memory with harness adaptation across scientific and interactive tasks.
Nov 9, 2026

Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists

Scientific discovery requires ideas that are original, useful, and non-obvious. Yet AI scientists are typically given as much task information as possible during idea generation, which can anchor generation toward familiar approaches. Inspired by the cognitive framework of Blind Variation and Selective Retention (BVSR), we propose a discovery framework that separates these two roles of information: it generates proposals under deliberately limited task information to broaden exploration, then learns from proposals previously verified on the same task and their outcomes to retain promising candidates for costly empirical evaluation. We evaluate BVSR across five proposer models and 12 scientific tasks. Limiting task information substantially increases proposal originality and non-obviousness, and produces a larger share of highly creative and high-utility proposals than existing state-of-the-art prompting-based baselines. Learning from prior proposal outcomes on the task further improves candidate selection, discarding half of the candidates while retaining most top-performing proposals. When incorporated into existing AI-scientist workflows, BVSR achieves stronger discoveries across gene expression analysis, drug response prediction, anomaly detection, scaling law discovery, and brain activity prediction. These results suggest that effective AI scientists should use information differently across stages of discovery: constrain task-specific information during exploration while exploiting accumulated empirical experience on the task.
Oct 23, 2026

Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical

AI systems that discover scientific relations now generate candidate "laws" at scale, but the bottleneck has shifted from generation to vetting: which candidates deserve belief? We show that a deployed self-improving science agent - one that has admitted 252 relations through held-out prediction courts - already computes the quantity that answers this question: the Minimum Description Length compression ratio used for model selection doubles, when read under discrete accounting, as an unsupervised epistemic grader. The compression-ranked top band of the agent's ledger recovers exactly the canonical laws among its discoveries (vis-viva across seven planets, Balmer/Rydberg) plus cross-measurement identities - enrichment p=3.6×10−12p=3.6\times10^{-12} under a hypergeometric test - with zero counterexamples and physically coherent band structure. The same lens retroactively reveals that 86% of the ledger compresses nothing (cr≈1\mathrm{cr}\approx 1): the agent had been recording statistical regularities, including a learned predictor with held-out R2=0.541R^2=0.541 admitted through the prediction gate, under a narrative of compression as the unified value of knowledge - a narrative that was never true for them. We formalize the resulting dual-axis bookkeeping - prediction value (R2R^2) and compression value (cr) as nearly decoupled axes of knowledge - demonstrate its robustness to quantization, and register forward falsifiable predictions. The episode is, to our knowledge, the first measured instance of a discovery agent auditing its own knowledge ledger by an internal measure and finding itself over-claiming.
Oct 21, 2026

SplatLab: Autonomous Scientific Discovery for 3DGS Research

Scientific discovery requires more than generating hypotheses: ideas must be grounded in prior work, translated into executable methods, experimentally validated, challenged by counterevidence, and communicated through reproducible findings. Despite recent advances in autonomous research agents, closing this entire loop remains challenging in rapidly evolving computer-vision fields with complex training pipelines and expensive evaluations. We introduce SplatLab, an autonomous scientific discovery system for 3D Gaussian Splatting (3DGS) that integrates literature understanding, hypothesis generation, implementation, experimental refinement, falsification, and manuscript writing into a unified research pipeline. Given a research prompt, a target-paper URL, or no input at all, SplatLab identifies research opportunities, proposes novel methods, trains and ablates candidates across Mip-NeRF 360 and LLFF, and produces manuscripts grounded in verifiable experimental evidence. Unlike prior systems, SplatLab performs discovery over verified baseline implementations using domain-aligned modification scaffolds. A cascade-weighted Elo tournament evolves candidate methods using measured GPU performance and verbal-gradient feedback, while a standing falsifier incorporates adversarial stress testing directly into selection. An integrity audit binds reported claims to logged experiments, and reviewer-driven feedback can initiate further experimentation rather than merely revising text. SplatLab discovers methods achieving PSNR improvements of +0.18 to +3.78 dB over matched baselines, including +3.78 dB on astrophotographic nebula rendering, a previously unexplored setting for 3DGS. By closing the loop between scientific reasoning, executable experimentation, and evidence-backed communication, SplatLab compresses months of researcher effort into days of mostly autonomous compute.
Oct 20, 2026

Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures

Autonomous agents can increasingly propose ideas, modify code, and run experiments, creating an opportunity to accelerate scientific discovery using teams of collaborative AI researchers. To escape local minima in the discovery, we propose to encourage orthogonal exploration by constructing the team using agents with varying expertise. However, realizing this design requires more than diverse backgrounds. When experiments are costly, a team can test only a limited number of ideas, thereby creating the need to balance exploration and exploitation when selecting a subset of researchers to propose and execute new experiments. Furthermore, each result should shape what the team tries next. We therefore ask how AI researchers with different scientific backgrounds can build on one another's findings and sustain progress under a limited experimental budget. To address these challenges, we build a team of persistent AI researchers, each grounded in a different discipline, who keep private research histories, share experimental evidence, and receive research opportunities through adaptive allocation. We demonstrate the effectiveness of this design by deploying the team to search for linear attention architectures, where it outperforms GDN2 at 1.3B scale on language modeling, common-sense reasoning, and synthetic and real-world retrieval tasks. In controlled comparisons, removing any single organizational component from our design yields markedly weaker discoveries: without disciplinary backgrounds, the search plateaus early; without private histories, researchers make less progress despite identical shared evidence; and uniform selection falls short of adaptive allocation within the same budget. These results suggest that sustained autonomous discovery depends not only on stronger agents, but also on who explores, what they remember, and how research effort is allocated.
Oct 20, 2026

OptScientist: Automated Discovery of Optimization Laws

Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused on recovering equations that describe observed input-output patterns. We introduce OptScientist, a novel automated framework for discovering compact symbolic optimization laws directly from data. OptScientist comprises (i) a model that infers symbolic optimization problems by first learning to represent data as an optimization problem and then extracting its symbolic form, and (ii) an LLM agentic system embedding the model in a discovery process that integrates theoretical priors from scientific literature, discovers candidate laws, abstracts their underlying mechanisms, and suggests new data to collect. We first evaluate OptScientist on OptFeynman, a novel benchmark of 99 physics-derived optimization problems, where OptScientist recovers ground-truth laws for over 80% of the problems and remains robust to noisy contextual information, while substantially outperforming machine-learning, symbolic, and LLM-based model-discovery baselines. On human risky choice and central-bank monetary policy, OptScientist discovers compact symbolic optimization laws that achieve held-out predictive performance competitive with leading baselines, while using few parameters and substantially fewer tokens than LLM baselines. Overall, OptScientist extends automated scientific discovery to uncovering optimization laws that generate observed phenomena, enabling automated theory building across the physical, biological, behavioral, and social sciences.
Oct 20, 2026

Agentic discovery of interpretable car-following laws from multi-source trajectory data

Car-following (CF) models is a fundamental component of microscopic traffic simulation and underpin the analysis of collective traffic dynamics, while its modeling becomes more challenging due to diverse human driving behaviors and the increasing presence of automated vehicle. Analytical CF models offer interpretable representations of longitudinal vehicle interactions, but their prescribed functional structures may limit the representation of heterogeneous driving behavior. This study proposes an agent-centered, physics-aware framework for the empirical discovery of CF laws from multi-source trajectory data. The framework iteratively combines agent-guided hypothesis generation, informed by traffic flow knowledge and state-dependent reconstruction errors, with evolutionary symbolic search and physics-aware multi-objective evaluation. Using NGSIM US-101, highD, and exiD, the framework discovers the Adaptive Equilibrium Response Model (AERM), which couples state-dependent relative-speed response with spacing-dependent equilibrium-speed restoration. AERM admits analytical equilibrium speed-spacing and flow-density relationships; its stability conditions are derived for the zero-delay formulation, and platoon simulations examine disturbance propagation. Evaluated against seven classical CF models on Shanghai naturalistic driving data, NGSIM I-80, and Waymo trajectories, AERM attains the lowest spacing and speed reconstruction errors under trajectory-specific calibration, reducing spacing RMSE by 9.11%, 7.59%, and 21.73% relative to the strongest baselines, and remains competitive under dataset-level shared parameters. These results demonstrate the fitting flexibility and analytical tractability of the discovered CF law, providing an interpretable basis for microscopic traffic simulation.
Oct 15, 2026

At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier

Recent breakthroughs in AI for mathematics---ranging from Olympiad medal performances to resolving long-standing open conjectures---have rapidly expanded what automated systems can achieve. Yet these successes primarily concern predefined, human-formulated problems, leaving open how AI systems can autonomously uncover mathematical structure and formulate new questions. To push beyond static challenges, we explore the Busy Beaver (BB) domain, an uncomputable frontier that is fundamentally open-ended. Because no algorithm can compute the Busy Beaver number BB(n)\mathrm{BB}(n) for every nn, this domain provides a natural setting for sustained exploration through mathematical conjecture and proof. In this paper, we introduce a Gemini-based agentic pipeline that automatically discovers accelerations of Turing machines, expressed as compact mathematical rules summarizing many execution steps. Our system integrates pattern recognition, automated conjecturing, informal mathematical reasoning, and formal theorem proving in Lean. With this framework, our system autonomously discovered and formally verified novel Collatz-like accelerations for eleven machines in BB(6)\mathrm{BB}(6). Subject to community acceptance, we provisionally classify these machines as Cryptids, namely machines whose blank-tape executions admit exact, compact mathematical descriptions but whose halting behavior remains unresolved. These results advance the analysis of BB(6)\mathrm{BB}(6) holdouts on the Busy Beaver frontier and demonstrate the potential of autonomous AI systems for open-ended mathematical discovery in fundamental computer science.
Oct 13, 2026

Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery

AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fixed datasets, while others that support active experimentation largely rely on simulation. We introduce Autonomous Science Bench, an initial release comprising six budgeted design-build-test-learn campaigns grounded in published experiments across biology, chemistry, and materials science. Agents select batches of designs, receive measurements from a lab service, and use the results to guide subsequent experiments before delivering a predictive model. Success requires passing two calibrated gates: a discovery gate, which evaluates the designs the agent measured, and a learning gate, which evaluates its model's ranking of held-out designs. In a pilot evaluation of ten agent-model configurations and 180 trials, the best configuration succeeds in 72% of trials, while the hardest campaign is solved in only five of 30 attempts. The two gates reveal different weaknesses: some agents build accurate rankings but find too few promising designs, while others find promising designs but fail to predict which unseen designs will perform well. These differences are obscured by overall success rates alone. We release version 0.1 of the campaigns, lab runtime, and public leaderboard at https://asb.open-ssi.org/.
Oct 10, 2026

Pre-Registered Genesis Accounting for Recursive Self-Improvement: First Audited Operator-Genesis Events in a Physics-Discovery Runtime

Claims of recursive self-improvement are easy to make and hard to falsify: did improvement come from re-using designer-provided mechanisms, or from mechanisms the system authored itself? We introduce a pre-registered, two-tier accounting: M1 counts machine-generated content instances within a designer-provided vocabulary, while M2 counts machine-authored mechanism types (new operators registered into the runtime's own vocabulary, with a held-out-validation certificate). We report the first audited M2 genesis events. In the primary event, depth-limited compositional search over elementary operators, judged by held-out R^2 on real NIST hydrogen Balmer measurements, produced the operator sq(inv(n)) = 1/n^2 -- the Rydberg-level form -- which no standard-library transform could express (held-out R^2: -0.546 best standard transform vs. 1.0000000 composed). A protocol flaw (independent variable built by inverting the very law under test) was caught in audit and repaired via an independent-label protocol; extrapolation to unseen levels (n=8,9 trained on n<=7) attains relative error ~10^-6, four to six orders beyond the best standard operator. A second event independently recovered sqrt(inv(a)) -- Kepler's velocity law -- from JPL ephemeris vectors. Also incorporated: an audited compounding channel (first domain-level measurement: 1.109x accuracy ratio on a real held-out domain) and blind, decurated genesis exams whose honest tally is zero. The Kepler event passes line audit; the hydrogen gap reproduces on He II; the certificate is threshold-stable. Against eleven prior systems, the contribution is the measurement and governance of machine-authored mechanisms, not the search algorithm or rediscovered physics. Limitations: exams were curated by agents who knew the textbook answer, triggers manual, grammar observer-injected; both events demonstrate capability to author, not yet autonomous genesis.
Oct 8, 2026

EvoSim: Learning to Model, Modeling to Learn

Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining states and governing equations, specifying couplings, and identifying parameters from experiments. Existing AI systems remain limited in making these model structure decisions autonomously. We introduce EvoSim, a self-evolving AI scientist for physical modeling. It uses experimental discrepancies to drive mechanism and equation revisions and held-out experimental data to test physical plausibility. Exploration traces make updates to knowledge, skills, and multi-agent orchestration. This co-evolution improves physics-based models and EvoSim's ability to select mechanisms, diagnose failures, and coordinate research. We evaluate EvoSim on two industrial battery modeling tasks. It predicts lithium-metal-plating onset from 25 to 45 degrees Celsius and 2 C to 6 C with a mean absolute error of 1.79% in state of charge. Dynamic voltage prediction under vehicle driving conditions achieves a root mean square error of 7.62 mV, surpassing the reported accuracy of models developed by human experts. Self-evolution reduces model and physics errors by approximately 36% relative to baseline, demonstrating improved scientific modeling capability. EvoSim turns experimental observations into validated models and cumulative research expertise.
Oct 8, 2026

Open-ended Scientific Discovery with Possibilistic Reasoning

Autonomous scientific discovery with LLMs requires generating and testing hypotheses adaptively as evidence accumulates while maintaining statistical validity. Existing anytime-valid methods can handle data-dependent hypotheses, but open-ended discovery poses a deeper challenge: the best discovered hypothesis may still be the best of a bad lot, with better explanations yet undiscovered, while even background knowledge such as physical laws may require revision in light of new findings. In response, we formalize the problem as Abductive Autonomous Scientific Discovery (AASD) using possibility theory. We introduce abductive utility, a computable measure of discovery progress, and possibility frontier search, the first algorithm for AASD, which maintains anytime validity and achieves ε\varepsilon-optimal abductive utility asymptotically under suitable conditions. Experiments on synthetic and real-world scientific-discovery tasks show strong performance.
Oct 8, 2026

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.
Oct 6, 2026

SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code

The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework that converts 3DGS papers into trainable gsplat-based implementations, where generic paper-to-code methods and frontier models fail. SPLATIFY achieves this through five innovations: (1) A context-free grammar for gsplat over a modular method template with extension points for losses, densification, rendering, and optimization, constraining synthesis so generated code satisfies gsplat's architectural invariants by construction. (2) Architectural elements for faithful reproduction: fork-aware citation recovery retrieving component-level code at function-level granularity, Graph-of-Thought synthesis in topological dependency order, RAG-guided in-context example selection from over 20 verified implementations, and visual feedback combining PSNR-guided regeneration, Gaussian-level structural checks, and VLM-driven patching. (3) Knowledge-driven compositional improvement that autonomously finds weaknesses and composes complementary regularizers, losses, and densification strategies to improve upon original results. (4) Interdisciplinary method discovery where agents retrieve physical priors from outside the 3DGS literature and compose them with rendering knowledge to produce methods for previously unaddressed scene types. (5) SPLATIFY-Bench, an evaluation framework across 30 diverse 3DGS papers. On papers without public code, SPLATIFY matches expert implementations while reducing development time from weeks to minutes, and through compositional discovery further improves PSNR by up to 2.4 dB. We additionally demonstrate novel methods for volumetric nebula rendering and other scientific domains, synthesized entirely by SPLATIFY.
Oct 6, 2026

Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station

Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they can autonomously undertake open-ended scientific discovery remains unclear. We investigate AI's ability to tackle open-ended tasks in Station, an open-world environment in which multiple agents simulate a scientific ecosystem. To tackle challenges specific to open-ended tasks, we propose augmenting Station with two mechanisms: a Supervisor mechanism and periodic Meta Reflection, which encourage persistent exploration even when intermediate metrics are lacking. We construct open-ended tasks from three recent oral papers presented at ICLR. We give agents the main research question studied in each paper while withholding the paper's results and disabling web access. We then measure how many of the original findings-partitioned into individual criteria-agents rediscover. We find that Station rediscovers 62.7% of the criteria on average, compared with 15.4% for Codex Multiagent-v2 and 14.4-20.6% for AI Scientist-v2. Ablation and behavioral analyses indicate that adding the two mechanisms together improves research coverage and continuity. We further evaluate Station on two open-ended tasks without oracle papers and find that some of the discoveries made by the agents closely match discoveries reported by researchers after the knowledge cutoff date. Together, these results indicate that a suitable environment can enable agents to autonomously make meaningful progress in open-ended scientific discovery.
Oct 4, 2026

AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding

Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only the role of proposer. The model knows nothing of the search beyond what it is shown. As models grow more capable, a question arises: does a search strategy chosen by a human before the run scale better than promoting the model from proposer to planner and letting it own the search? The Bitter Lesson suggests that choosing the strategy in advance is the kind of hand-designed structure that general methods eventually outscale. We introduce AgentDiscover, in which a coding agent plans the search using its context as working memory, runs experiments, and records every attempt in a database of ideas, candidates, and their relations. This database serves as the agent's long-term memory and is structured so that the selection rules of classical algorithms such as MAP-Elites and Monte Carlo tree search each reduce to a single query, which the agent is free to use, combine, or replace. A server maintains the database and steers the agent after every submission, keeping it on course over long runs. In our experiments, AgentDiscover is more cost-efficient than existing frameworks, reaching better scores at lower cost. On tasks in kernel engineering, biology, algorithm design, and mathematics, AgentDiscover outperforms prior discovery frameworks. Its programs would have placed first among human competitors in seven past AtCoder heuristic contests, and on eleven mathematical and systems optimization tasks it matches or exceeds every baseline that uses the same model. Our code is available at https://github.com/mhdfb/AgentDiscover.
Oct 4, 2026

GitSwarm: Decentralized Compounding Inference

Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental findings, and unsuccessful approaches can inform later work, yet most inference-time computation is organized around individual trajectories or candidates rather than a persistent body of reusable work. We call this paradigm compounding inference: organizing inference-time computation so that intermediate work persists and can be inspected, extended, combined, or challenged by subsequent computation. We instantiate compounding inference in GitSwarm, an asynchronous system where homogeneous agents independently decide how to advance a task while collaborating through structured persistent memory. Agents explore, experiment, verify, refine, and synthesize previous work in a shared, branch-able Git repository. Atomic commits preserve intermediate artifacts, while explicit semantic dependencies record how later contributions build on work across branches. We evaluate GitSwarm on long-horizon problem solving and sustained GPU-backed experimental research. On IMOProofBench-Advanced, GitSwarm solves all 30 problems in one run using GPT-5.5. On ProgramBench, it achieves a 79.4%79.4\% mean score, versus 65.1%65.1\% for the strongest reported baseline under the stated budget. On three neural architecture research tasks (Residual Matrix Transformer, Looped Transformer, NanoChat), GitSwarm improves upon the starting architectures through successive experimentation. Beyond final performance, we measure whether computation accumulates: on ProgramBench, 94.7%94.7\% of contributions are subsequently built upon, while the selected solution's ancestry covers 82−93%82-93\% of the contribution graph. These results show that inference-time computation can accumulate across otherwise independent episodes, forming an evolving body of work that subsequent inference can reuse.
Oct 2, 2026

ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe

Scientific discovery often begins when scattered clues call for a new way of describing the world. Such abductive exploration can require constructing the representation in which an explanation is stated, when the world is epistemically open, and composing evidence scattered across contexts, when it is structurally interconnected. Existing benchmarks rarely separate these two demands or control them independently. We introduce ULTRADISCOVERY, an interactive world of five domains in which an agent revises an initially successful theory and predicts the outcome of an unseen cross-domain intervention. A 2×22 \times 2 design leaves the representation open or discloses it, and leaves the evidence distributed or aligns it, with the latent dynamics fixed. With the representation open, agents across eleven models often retract the axiom they were taught, and none introduces the unobserved entity or rewrites the variables that a replacement requires. Disclosure triples intervention requests and adds about one of the eighteen findings the world affords, and alignment adds less. Two vendor-harness systems carry discovery into more domains, and one of them rewrites the variables in Open episodes. No system makes the exact prediction within 200 paid actions. At larger budgets one exact prediction appears with both aids, while every Open episode remains inexact. The results locate the difficulty in the step from accumulating evidence to composing it into a representation that transfers.
Oct 1, 2026

The AI Theorist reveals excitonic structure in αα-RuCl3_3

Advances in experimental instrumentation and automation generate increasingly rich datasets, but turning experimental observations into microscopic understanding remains a bottleneck in scientific discovery. To accelerate this process, we introduce AI Theorist, a system of artificial intelligence (AI) agents for autonomous discovery of physical models through hypothesis generation, first-principles calculations and evidence-driven refinement. We apply the framework to αα-RuCl3_3, a leading candidate material for realizing a Kitaev quantum spin liquid, to investigate its electronic structure through optical spectra. AI Theorist develops a new interpretation of the optical and photocurrent observations, identifying distinct excitonic states with contrasting optical selection rules and real-space distributions. To our knowledge, this is the first demonstration of an AI system autonomously developing a physical model to explain previously unpublished experimental observations in a quantum material, utilizing first-principles electronic-structure and many-body calculations. Our results establish a route to autonomous theoretical discovery in materials science, in which AI agents use first-principles calculations to turn experimental observations into physical models and testable predictions.
Oct 1, 2026

Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings

Modern computational methods can now propose candidate molecules, materials, and other scientific designs at an unprecedented scale, creating a validation congestion where candidates are abundant, but experimental capacity to physically evaluate them remains scarce. Discovering novel scientific designs has therefore become increasingly dependent on curation: selecting a small set of promising designs for slow and costly experiments. Existing curation methods typically rely on data-driven regression models that predict absolute scores, but training these models requires substantial experimental data to begin with. Yet, useful curation signals do not have to take the form of absolute measurements, as scientific design discovery is often comparative in nature. Here, we propose that curation can instead be primarily driven by expert pairwise rankings, which are substantially easier to gather. The expertise can come from computational tools or human input of multiple levels of fidelity, ranging from empirical rules of thumb to agentic workflows and experienced scientists. We introduce PRISMS, a framework that uses pairwise rankings from one or more experts, potentially spanning multiple levels of expertise, to identify the most promising candidates without relying on data-hungry regressors. When experts differ in fidelity and cost, PRISMS escalates pairwise queries from lower- to higher-fidelity rankers based on a Fisher-information criterion. In iterative screening that selects designs from fixed drug discovery libraries, PRISMS achieves 50% top-10 discovery recall in ~42% fewer rounds than regression-only active learning, and in ~15% fewer rounds than the ranking-based method with no selective escalation. In optimization that generates new designs without restriction to a predefined library, PRISMS achieves ~18.8% higher hypervolume than the Bayesian optimization baseline.
Sep 30, 2026

EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights

When Isaac Newton discovered the law of gravitation, he did so through an iterative process of analyzing observed data such as planetary patterns, finding the underlying mechanisms by describing patterns in mathematical equations, and refining his theory against the Moon's orbit, revealing the startling insight that the same force governs both falling apples and orbiting planets. Would it be possible for AI agents to make similar discoveries? To measure this ability, we introduce EurekaBench, a cross-domain benchmark that tests AI agents' ability to conduct long-horizon experiments and discover mechanisms that explain observations. We evaluate these mechanisms by the scientific insights that can be derived from them. EurekaBench contains an expert-verified set of 26 long-horizon tasks across neuroscience, computer science, chemistry, astrophysics, geophysics, and plasma physics, with a total of 306 scientific insights that the discovered mechanisms are expected to support. Our evaluation framework tests three axes of scientific discovery: agents' ability to follow known scientific constraints, the predictive accuracy of the discovered mechanisms, and whether these mechanisms yield scientific insights or inform future research. Our results show that current AI agents often overly fixate on predictive accuracy optimization, surpassing human scientists, while falling substantially short in deriving scientific insights.
Sep 29, 2026

Can an AI Agent Rediscover a Blaschke-Curve Invariant?

We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery. For one fixed degree-four Blaschke product, an agent receives numerical coordinates of the six pair-lines determined by each of 80 boundary configurations. The target theorem is withheld from the task instructions. The saved research log reports rejected geometric hypotheses and a homogeneous cubic fitted to polygon sides. Its frozen coefficients predict 480 lines from 80 unseen parameter values, with a recorded RMS scale-free residual of 8.88×10−178.88\times10^{-17}. Discovery-set diagonals provide an out-of-fit consistency check, not a fully held-out test. A separate one-configuration run reports insufficient evidence for invariance. A post-review deterministic degree-search baseline also recovers the cubic, so the experiment does not establish an advantage over polynomial fitting. We present this single-instance case study as a protocol for separating conjecture, numerical validation, and proof, with explicit limitations concerning agent metadata, prior knowledge, and reproducibility.
Sep 29, 2026

AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks

With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet, recent progress in the field of LLM watermarking has increasingly been driven by improving details of existing methods, an effort fundamentally limited by the pace of human researchers. In this work, we enable for the first time the autonomous discovery of new distortion-free state-of-the-art watermarking schemes. To enable this, we (i) establish strict criteria to ensure that watermarks are reliable (e.g., they do not have an unexpectedly high false positive rate), (ii) propose rigorous statistical tests to automatically evaluate whether a watermarking scheme satisfies our criteria, and (iii) design an evaluation suite to rank watermarks along three key dimensions: detectability, quality, and robustness. By running our framework with 3 frontier models (GPT-6 Astra, Opus 5, Gemini-3.8 Flash), we discover over 50 different watermarking schemes, including several that outperform prior works along all key dimensions. We complement this by a manual study of the discovered schemes, distilling the key ideas into smaller components, and individually studying the impact of each component across dimensions (detectability, quality, robustness) to better understand how the proposed schemes operate. Importantly, we find that the agents, on top of improving existing ideas, also discover fundamentally new ideas (e.g., aligning watermark scores with random per-request direction). Overall, our work establishes the first steps of fully autonomous watermarking research, enabling the discovery of more reliable and effective watermarks. Our code is available at https://github.com/eth-sri/automark, and a blogpost to visualize our results at https://www.sri.inf.ethz.ch/blog/automark.
Sep 28, 2026

DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery

We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.