AI Agents for Scientific Discovery

Ask about this topic

Overview

AI agents for scientific discovery aim to help researchers move from questions and hypotheses to analysis, experiments, and evidence-backed conclusions. Common approaches combine language models with literature retrieval, code execution, scientific simulators, laboratory instruments, and specialized agents in iterative hypothesis–test–revision loops. Work spans fields such as materials science, biology, physics, chemistry, and mathematics, with systems also developing reusable skills and memories to build on prior results. A central challenge is ensuring that promising outputs are genuinely novel, scientifically valid, reproducible, and grounded in evidence, especially in long workflows and physical experiments.

Latest papers

CardsList

292 papers57 papers in the last four weeks, up 111% on the four weeks before. 0.3% of all new papers.

May 11, 2026

An agentic framework for gravitational-wave counterpart association in the multi-messenger era

With the detection of gravitational waves (GWs), multi-messenger astronomy has opened a new window for advancing our understanding of astrophysics, dense matter, gravitation, and cosmology. The GW sources detected to date are from mergers of compact object binaries, which possess the potential to generate detectable electromagnetic (EM) counterparts. Searching for associations between GW signals and their EM counterparts is an essential step toward enabling subsequent multi-messenger studies. In the era of next-generation GW and EM detectors, the rapid increase in the number of events brings not only unprecedented scientific opportunities, but also substantial challenges to the existing data analysis paradigm. To help address these challenges, we develop GW-Eyes, an agentic framework powered by large language models (LLMs). For the first time, GW-Eyes integrates domain-specific tools and autonomously performs counterpart association tasks between GW and candidate EM events. It supports natural language interaction to assist human experts with auxiliary tasks such as catalog management, skymap visualization, and rapid verification. Our framework leverages the complex decision-making capabilities of LLMs and their traceable reasoning processes, offering a new perspective to the multi-messenger astronomy.

Yiming Dong, Yacheng Kang, Junjie Zhao +3

Department of Astronomy, School of Physics, Peking University, No. 5 Yiheyuan Road, Beijing, 100871, Beijing, China. · Kavli Institute for Astronomy and Astrophysics, Peking University, No. 5 Yiheyuan Road, Beijing, 100871, Beijing, China. · Institute for Gravitational Wave Astronomy, Henan Academy of Sciences, No. 228 Chongshili Road, Zhengzhou, 450046, Henan, China. +2

AI Agents for Scientific DiscoveryGravitational-Wave AstronomyLLM Agents
AskPDF
May 11, 2026

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems

AI scientist systems are increasingly deployed for autonomous research, yet their academic integrity has never been systematically evaluated. We introduce SCIINTEGRITY-BENCH, the first benchmark designed around a dilemmatic evaluation paradigm: each of its 33 scenarios across 11 trap categories is constructed so that honest acknowledgment of failure is the only correct response, while task completion requires misconduct. Across 231 evaluation runs spanning 7 state-of-the-art LLMs, the overall integrity problem rate reaches 34.2%, and no model achieves zero failures. Most strikingly, across missing-data scenarios, all seven models generate synthetic data rather than acknowledging infeasibility, differing only in whether they disclose the substitution. A further prompt ablation study separates two drivers: removing explicit completion pressure sharply reduces undisclosed fabrication from 20.6% to 3.2%, while the underlying synthesis rate remains unchanged, revealing an intrinsic completion bias that persists independent of prompt-level instructions. These findings point to the absence of honest refusal as a trained disposition as the primary driver of observed failures. We release SCIINTEGRITY-BENCH at https://github.com/liuxingtong/Sci-Integrity-Bench.

Zonglin Yang, Xingtong Liu, Xinyan Xu

Readraft Lab · Peking University · Tongji University +1

AI Agents for Scientific DiscoveryAI Agent EvaluationAI Agent BenchmarksLLM HonestyAcademic Integrity
AskPDF
May 9, 2026

Evolutionary Ensemble of Agents

We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as optimizers" paradigm, EvE fixes the base agent substrate and focuses entirely on evolving the cumulative guidance and skills that dictate agent behaviors. By maintaining two co-evolving populations, namely functional code solvers and agent guidance states, the system evaluates agents through a synchronous race, updating their empirical Elo ratings based on the marginal gains they contribute to the current solver state. When applied to a research bottleneck in In-Context Operator Networks (ICON), EvE autonomously discovered a robust rescale-then-interpolate mechanism that enables reliable example-count generalization. Crucially, controlled ablations reveal the absolute necessity of stage-dependent agent adaptation to navigate the shifting search landscapes of complex codebases. Compared to variants driven by a fixed initial agent or even a frozen "best-evolved" agent, EvE uniquely avoids phase mismatch, demonstrating that organizing agents into a self-revising ensemble is the fundamental driver for breaking through static performance ceilings.

Zongmin Yu, Liu Yang

National University of Singapore

AI Agents for Scientific DiscoveryEvolutionary OptimizationMulti-Agent CodingSelf-Evolving Agents
AskPDF
May 9, 2026

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery

A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery. We identify the following challenges in building and deploying autonomous AI scientists: (1) Problem selection is influenced by the McNamara fallacy; (2) Agents are built on large language models (LLMs) whose training corpora omit tacit procedural and failure knowledge of laboratory practice; (3) Preference optimisation during post-training compresses output diversity toward consensus; and (4) Most scientific benchmarks measure single-turn prediction accuracy and lack feedback from physical experiments back to the computational model. These challenges are not just questions of scale and scaffolding; they require revisiting fundamental design choices. To build truly autonomous AI scientists, we recommend the use of scientific simulations as verifiers for training, the design of persistent world models that represent the shifting objectives governing real investigations, the establishment of a centralized preregistration repository for all AI-generated hypotheses, and application driven by scientific need rather than tool affordance.

Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka +2

Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena · Center for Energy and Environmental Chemistry Jena, Friedrich Schiller University Jena +3

AI Agents for Scientific DiscoveryScientific Hypothesis GenerationAutonomous Scientific DiscoveryLarge Language Model-Guided Scientific Discovery
AskPDF
May 9, 2026

MDGYM: Benchmarking AI Agents on Molecular Simulations

The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dynamics (MD) simulation presents a natural test bed to stress-test this claim; it requires translating physical intuition into syntactically and semantically correct input scripts, reasoning about initial and boundary conditions, diagnosing numerically unstable trajectories, and interpreting outputs against known physical behavior and laws. We introduce MDGYM, a benchmark of 169 expert-curated MD simulations spanning LAMMPS and GROMACS, two widely used MD packages, across three increasing difficulty levels. We evaluate three agentic frameworks -- Claude Code, Codex, and OpenHands -- with four LLMs, and find that all perform poorly: even the strongest agent solves only 21% of easy-level tasks, with less than 10% at higher difficulties. Trajectory analysis reveals a characteristic pattern of failure -- agents successfully invoke simulation machinery but produce physically unstable configurations, fabricate numerical outputs without executing the underlying computation, or abandon tasks prematurely rather than iterating through simulation-specific errors. These failure modes are qualitatively distinct from those observed in general software engineering benchmarks, indicating that fluent code generation does not transfer to grounded physical reasoning.

Vinay Kumar, Satyendra Rajput, Mausam +1

Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Department of Computer Science and Engineering, Indian Institute of Technology Delhi · Department of Civil and Environmental Engineering, Indian Institute of Technology Delhi +1

AI Agents for Scientific DiscoveryAI Agent EvaluationAI Agent BenchmarksScientific Workflow AutomationMolecular Dynamics Simulation
AskPDF
May 9, 2026

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is increasingly important to understand whether they can discover such methods rather than only apply existing ones. We introduce MLS-Bench, a benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods. MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings and scales. We find that current agents remain far from reliably surpassing human-designed methods, and that engineering-style tuning is easier for them than genuine method invention. We further study the effects of test-time scaling, adaptive compute allocation, and context provision on agents' discovery performance, together with case studies of their behavior. Our analyses suggest that the bottleneck is not only in proposing new methods, but also in the scientific insight needed to plan, validate, and scale claims about them. More search, compute, or context alone does not remove this bottleneck. We build and maintain a community platform for cumulative and comparable iteration, and release the data and code at https://mls-bench.com.

Bohan Lyu, Yucheng Yang, Siqiao Huang +25

UC Berkeley · Tsinghua University · Purdue University +6

AI Agents for Scientific DiscoveryAutomated Algorithm DiscoveryAI Agent BenchmarksAutomated Machine LearningLarge Language Model-Guided Scientific Discovery
AskPDF
May 8, 2026

ADKO: Agentic Decentralized Knowledge Optimization

We present Agentic Decentralized Knowledge Optimization (ADKO), a framework for collaborative black-box optimization across autonomous agents that achieves sample efficiency, privacy preservation, heterogeneous-objective handling, and communication efficiency. Each agent maintains a private Gaussian Process (GP) surrogate trained on local data and communicates only through knowledge tokens-compact, lossy summaries containing directional signals, advantage scores, and optional language-model (LM) insights-without sharing raw data or model parameters. ADKO unifies GP-Upper Confidence Bound (GP-UCB), parallel Bayesian optimization, decentralized learning, and LM-guided discovery. We provide the first formal analysis of dual information loss: token compression, quantified via mutual-information-based fidelity, and LM approximation error, decomposed into bias and stochastic noise. Our main result shows cumulative regret decomposes into GP error, LM bias, LM noise, and compression loss, with necessary and sufficient conditions for sublinear regret. We also propose fidelity-aware token pruning to preserve high-information tokens under memory budget. Experiments on neural architecture search and scientific discovery validate the theory and show consistent improvements over strong baselines.

Lucas Nerone Rillo, Zhanhong Jiang, Nastaran Saadati +4

Iowa State University · New York University

Multi-Agent System OptimizationAI Agents for Scientific DiscoveryBayesian OptimizationBlack-Box OptimizationLarge Language Model-Guided OptimizationDecentralized Optimization
AskPDF
May 8, 2026

Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation

Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering ordinary differential equations with LLM-based qualitative and quantitative evaluation. DoLQ employs a multi-agent architecture: a Sampler Agent proposes dynamic system candidates, a Parameter Optimizer refines equations for accuracy, and a Scientist Agent leverages an LLM to conduct both qualitative and quantitative evaluations and synthesize their results to iteratively guide the search. Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations. Our code is available at https://github.com/Bon99yun/DoLQ.

Sum Kyun Song, Bong Gyun Shin, Jae Yong Lee

Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea · Department of AI Big Data, Daejin University, Pocheon-si, Republic of Korea.

AI Agents for Scientific DiscoveryAutonomous Scientific DiscoveryLarge Language Model-Guided Scientific DiscoveryODE DiscoverySymbolic RegressionOrdinary Differential Equations
AskPDF
May 8, 2026

Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning

Large Language Models (LLMs) have become increasingly capable as tool-using agents, with benchmarks spanning diverse general agentic tasks. Yet rigorous evaluation of scientific tool use remains limited. In chemistry, recent agents can plan syntheses and invoke domain-specific tools, but evaluations often rely on curated demonstrations, expert assessment, or LLM-as-judge scoring rather than exact, judge-free ground truth. We address this gap with chemical procurement cost estimation, a practical task in which an agent must ground chemical identities, retrieve supplier quotes, select valid purchasable packs, normalize quantities, and compute cost from a reaction description. We introduce ChemCost, a benchmark of 1,427 evaluable reactions grounded to a frozen pricing snapshot covering 2,261 chemicals and 230,775 supplier quotes, supporting scalar scoring and stage-level diagnosis of grounding, retrieval, procurement, and arithmetic failures. To evaluate robustness, we further construct controlled noise-injected views that perturb chemical aliases, quantity expressions, missing fields, and input formatting. Experiments with frontier, open-weight, and chemistry-specialized LLM agents show that tool access is necessary but insufficient for solving the task. The strongest agents reach only 50.6% accuracy within 25% relative error on clean inputs and degrade substantially with realistic noise. Stage-level analysis further shows that failures arise from brittle parsing, ineffective evidence integration, invalid pack selection, and non-convergent tool use.

Yuyang Wu, Yue Huang, Shuaike Shen +8

Carnegie Mellon University · University of Notre Dame · University of North Carolina, Chapel Hill +1

AI Agents for Scientific DiscoveryLLM Agent EvaluationAI Agent BenchmarksLLM Tool UseLLM Agent ReliabilityChemical Reasoning in LLMs
AskPDF
May 7, 2026

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage. We show that PubMed itself can be autonomously and cost-effectively turned into structured datasets that are larger, more nuanced, and more accurate than the curated databases they replace. We present three coupled contributions: (1) an LLM-based entity-tagging pipeline, grounded in nine biomedical ontologies, that tags 4.5B entities across 19 categories in a 22.5M-paper, 2.5T-token PubMed corpus; (2) hybrid sparse-dense retrieval supporting entity-filtered semantic queries over the tagged corpus; and (3) Starling, a multi-agent deep research system that, given only a natural-language task description, designs precision- and recall-targeted retrieval filters, induces an extraction schema, and emits structured records with nuance-rich fields and supporting passages. Across six tasks -- blood-brain barrier permeability, oral bioavailability, acute toxicity (LD50), gene-disease associations, protein subcellular localization, and chemical reactions -- Starling produces ~6.3M records (91K-3M per task); several are, to our knowledge, the largest public datasets for their property. Frontier-model rejection of our extractions is 0.6-7.7% across tasks, far below error rates we measure on widely used curated counterparts (e.g., 16.5% on BBB_Martins, 7.3% on Bioavailability_Ma). Beyond scale and accuracy, the supporting passages carry nuance tabular databases discard -- e.g., oral bioavailability may depend on fed vs. fasted state. Together, the corpus, retrieval, and agent establish a foundation for AI-driven therapeutic design. Code and datasets: https://github.com/starling-labs/starling.

Haydn Jones, Yimeng Zeng, Alden Rose +11

Department of Computer and Information Science, University of Pennsylvania · Department of Genetics, University of Pennsylvania · 3Departments of Bioengineering and Chemical and Biomolecular Engineering,2026 University of Pennsylvania

AI Agents for Scientific DiscoveryLLM Information ExtractionBiomedical IR
AskPDF
May 7, 2026

AI co-mathematician: Accelerating mathematicians with agentic AI

We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.

Daniel Zheng, Ingrid von Glehn, Yori Zwols +15

Google DeepMind · Google

AI Agents for Scientific DiscoveryAI-Assisted Mathematical DiscoveryAI-Assisted Scientific ResearchHuman-AI CollaborationLLM Mathematical ReasoningAutonomous Research Agents
AskPDF
May 7, 2026

AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents

Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning research, in chemistry, and in biology. Extending the same loop to high-fidelity physical simulators is harder, because solver completion does not imply physical validity and many failure modes appear only in field-level imagery rather than in solver logs. We present AI CFD Scientist, an open-source AI scientist for computational fluid dynamics (CFD) that, to our knowledge, is the first to span literature-grounded ideation, validated execution, vision-based physics verification, source-code modification, and figure-grounded writing within a single inspectable workflow. Three coupled pathways cover parameter sweeps within a fixed solver, case-local C++ library compilation for new physical models, and open-ended hypothesis search against a reference comparator, all running on OpenFOAM through Foam-Agent. At the center of the framework is a vision-language physics-verification gate that inspects rendered flow fields before any result is accepted, rerun, or written into a manuscript. On five tasks under a shared GPT-5.5 backbone, AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction that reduces lower-wall Cf RMSE against DNS by 7.89% on the periodic hill at Reh=5600; under matched LLM cost, two strong general AI-scientist baselines (ARIS, DeepScientist) execute partial CFD workflows but lack the domain-specific validity gates needed to convert runs into defensible scientific claims; and a controlled planted-failure ablation shows that the vision-language gate detects 14 of 16 silent failures missed by solver-level checks. Code, prompts, and run artifacts are released at https://github.com/csml-rpi/cfd-scientist.

Nithin Somasekharan, Rabi Pathak, Manushri Dhanakoti +4

1Rensselaer Polytechnic Institute

AI Agents for Scientific DiscoveryAutonomous Scientific DiscoveryScientific Workflow AutomationComputational Fluid Dynamics
AskPDF
May 7, 2026

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents

Reproducing and comparing deep research agents today is hard: the same backbone evaluated on the same benchmark can report different accuracies across papers because the harness and tool registry differ, and integrating a new model into a comparable evaluation surface costs weeks of model-specific engineering. These are symptoms of a broader reproducibility problem in deep research agent research. Here, we introduce BioMedArena, an open-source toolkit that addresses this reproducibility gap and provides an arena for comparing deep research agents under a shared evaluation environment. BioMedArena decouples six layers of biomedical agent evaluation -- benchmark loading, tool exposure, tool selection, harness mode, context management, and scoring -- and exposes 166 biomedical benchmarks and 75 biomedical tools across 9 functional families. Adding a new model, benchmark, or tool can be accomplished with a few-line provider adapter. Beyond evaluation infrastructure, BioMedArena ships a library of high-quality reference components: 6 agent harnesses (including our proposed Mutual-Evolve) and 6 context-management strategies, any of which can be equipped on any backbone. Equipping these components substantially improves all 12 backbones; on each of 8 representative biomedical benchmarks, the best equipped backbone surpasses prior state-of-the-art (SOTA), by 15.01 percentage points on average. The toolkit, configurations, and per-task traces are available at https://github.com/AI-in-Health/BioMedArena.

Jinge Wu, Hongjian Zhou, Mingde Zeng +8

University of Oxford · University College London · Technical University of Munich +1

AI Agents for Scientific DiscoveryDeep Research AgentsAI Agent EvaluationAI Agent BenchmarksML Reproducibility
AskPDF
May 7, 2026

BioResearcher: Scenario-Guided Multi-Agent for Translational Medicine

Translational medicine turns underspecified development goals into evidence synthesis that must combine literature, trials, patents, and quantitative multi-omics analysis while preserving identifiers, uncertainty, and retrievable provenance. General-purpose foundation models and off-the-shelf tool-augmented or multi-agent systems are not built for this: they tend to produce single-shot answers or run open-endedly, and fall short on the auditable, scenario-specific workflows that heterogeneous biomedical sources demand. This paper introduces Ingenix BioResearcher, a scenario-guided multi-agent system that maps queries to versioned research playbooks, delegates to specialized subagents over 30+ tools and machine-learning endpoints, mixes structured database access with sandboxed code for genome-scale analyses, and applies claim-level multi-model reconciliation before editorial assembly. We evaluate BioResearcher across unit-level capabilities, open-ended biomedical reasoning, and end-to-end clinical discovery. It leads evaluated baselines on 109 single-step tests (83.49% pass rate; 0.892 average score), achieves strong biomedical benchmark performance (89.33% on BixBench-Verified-50 and the top 0.758 mean score on BaisBench Scientific Discovery), and leads on a 30-query clinical end-to-end benchmark with the highest positive hit rate (74.7% ±\pm 3.3%) and negative clear rate (96.8% ±\pm 0.2%). These results show broad, competitive performance across unit-level, open-ended, and end-to-end clinical evaluations.

Remigiusz Kinas, Joanna Krawczyk, Rafał Powalski +6

Ingenix.AI, Warsaw, Poland

Multi-Agent OrchestrationAI Agents for Scientific DiscoveryHealthcareScientific Workflow Automation
AskPDF
May 6, 2026

Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery

To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to scientific discovery. While some tasks can be performed on a computer (e.g., data analysis, running simulated experiments), Eureka moments could occur at any time while operating lab instruments (e.g., when a scientist notices unexpected clues, intuition may prompt a real-time course change). Although autonomous labs are on the rise, which expose programmable APIs to control scientific instruments via software, bridging the gap between increasingly powerful AI agents and automated lab equipment requires innovation that draws insights from computer systems. We propose a new paradigm called ``Experiment-as-Code (EaC) Labs,'' where a core concept is to encode experiments as declarative configurations that can be compiled down to device-level APIs. AI agents come up with hypotheses and experiments, written as an ensemble of declarative configurations. The systems layer performs program analysis, safety checks, resource assignment, and job orchestration. Finally, programmatic experimentation occurs via actuating the device APIs. This is a general stack that is science-, lab-, and instrument-independent, representing a novel synthesis across the physical, systems, and intelligence layers to unleash the next breakthrough in AI for Science.

Zhenning Yang, Yuhan Chen, Patrick Tser Jern Kon +5

University of Michigan

AI for ScienceAI Agents for Scientific DiscoveryLaboratory AutomationScientific Workflow AutomationAutonomous Experimentation
AskPDF
May 4, 2026

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry.

Aritra Roy, Kevin Shen, Andrew MacBride +350

Multi-Agent LLM SystemsAI Agents for Scientific DiscoveryLLM Tool Use
AskPDF
May 4, 2026

An explainable hypothesis-driven approach to Drug-Induced Liver Injury with HADES

Drug-induced liver injury (DILI) remains a leading cause of late-stage clinical trial attrition. However, existing computational predictors primarily rely on binary classification, a framing that limits generalization and yields no mechanistic insight to guide translational decisions. We argue that DILI prediction is better posed as an explainable hypothesis-generation problem. To support this shift, we introduce the DILER Benchmark, a dataset that extends beyond binary labels by augmenting a curated set of molecules with mechanistic hepatotoxicity hypotheses derived from biomedical literature. We further present HADES, an agentic system designed to generate transparent and auditable reasoning traces. By combining molecular-level predictions, metabolite decomposition, structural understanding, and toxicity pathway evidence, HADES mechanistically assesses DILI risk. Evaluated on the DILER Benchmark, HADES outperforms existing models in binary classification, achieving a ROC-AUC of 0.68 on the Test Set and 0.59 on the challenging Post-2021 Set, compared with 0.63 and 0.50 for DILI-Predictor, respectively. More importantly, we establish a baseline for mechanistic hypothesis generation, where HADES achieves a Hypothesis Alignment Fuzzy Jaccard Index of 0.16. This result underscores the inherent complexity of the task while highlighting the need for advanced explainable approaches in predictive toxicology.

Maciej Wisniewski, Bartosz Topolski, Pawel Dabrowski-Tumanski +2

Ingenix.ai, Warsaw, Poland · Laboratory of Bioinformatics and Computational Genomics, Warsaw University of Technology, Warsaw, Poland · Laboratory of Functional and Structural Genomics, Centre of New Technologies, University of Warsaw, Warsaw, Poland

Explainable Artificial IntelligenceAI Agents for Scientific DiscoveryScientific Hypothesis GenerationToxicity Detection
AskPDF
May 1, 2026

Agents and Tokens: Multi-Agent Autonomous Reasoning over a Hydrodynamic Token Store

Large language models and the agents built on them are the most capable reasoning machines ever built, and science is beginning to put them to work. Atmospheric and oceanic sciences are starting to see agentic integration, but coastal hydrodynamics remains largely untouched by AI. Simply, agents cannot easily read its data products without saturating their context windows. A time frame from a coastal model can hold hundreds of megabytes, and if the archive's chunking does not suit the query, the agent will spend more time downloading and compacting than gaining insights. After all, the archives were designed for storage, not for the fast, on-the-fly access agents need. Speech and music once hit the same wall. A minute of audio is millions of numbers, yet today's audio models hold conversations and write music. They "learned" to do this by "listening" to tokens. Neural audio codecs turn waveforms into short sequences of discrete symbols that a model reads like words and decodes back into sound. Coastal water is a similar signal: dense, finely sampled, and repeatable. We are convinced it has an analogous compact native representation that preserves the salient physics. Tokens are that representation: small integers, light enough for an agent to sweep six months of a coastline in seconds. Agents can then do more than simple lookup-related tasks; they can form and test their hypotheses as they explore the tokenized representation efficiently. Herein, we build this framework, using vector quantized variational autoencoders to compress tide level, the non-tidal residual, and surface wind speed into 16x16 grids of tokens along the US Atlantic and Gulf coasts. Agents traverse and explore these grids (e.g., tracking, spatiotemporal trend analysis) considerably faster than raw archives in both on-prem and off-prem modalities, while correctly answering several types of under-specified queries.

Jinpai Zhao, Albert Cerrone, Joannes Westerink +1

Oden Institute University of Texas at Austin Austin, Texas, USA · CEEES University of Notre Dame Notre Dame, Indiana, USA

Multi-Agent OrchestrationAI Agents for Scientific DiscoveryMulti-Agent ReasoningLLM Agent Reliability
AskPDF
May 1, 2026

Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output

Scientific discovery is an extended process of ideation -- surveying prior work, forming hypotheses, and refining reasoning -- yet existing LLM research agents treat this phase as a brief preamble despite its central role in research. We introduce SciSense, a sensemaking-grounded framework that operationalizes ideation as a structured sequence of eight cognitive stages (Pirolli and Card, 2005). We construct SciSense-Traj, a dataset of 120K citation-conditioned research trajectories in two modes: Hindsight, where an LLM reconstructs the ideation path from a paper's cited works to the paper itself, and Foresight, where the LLM proposes novel directions from the same citations. We distill these into SciSense-LM, a family of sensemaking LLMs spanning 3B to 70B parameters. Contrary to the assumption that looser supervision promotes exploration, Hindsight-trained models improve trajectory quality by 2.0% over Foresight-trained models while also producing more novel and diverse outputs, across all eight model families we test. The advantage propagates downstream: coding agents conditioned on Hindsight trajectories produce research artifacts with higher executability, scientific grounding, and utility than those conditioned on Foresight trajectories. This suggests that outcome-anchored ideation reduces the cognitive burden on downstream agents, freeing them to explore more creatively. SciSense offers both a practical tool for augmenting LLM-driven research workflows and a principled testbed for studying how planning shapes scientific discovery.

James Mooney, Zae Myung Kim, Young-Jun Lee +1

University of Minnesota

AI Agents for Scientific DiscoveryScientific Hypothesis GenerationResearch Idea GenerationLarge Language Model-Guided Scientific Discovery
AskPDF
Apr 30, 2026

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

Despite recent progress in language models and agents for scientific data-driven discovery, advancing their capabilities is held back by the absence of verifiable environments representing real-world scientific tasks. To fill this gap, we introduce D3-Gym, the first automatically constructed dataset with verifiable environments for scientific Data-Driven Discovery. D3-Gym comprises 565 tasks from 239 real scientific repositories across four disciplines, each with a natural language instruction, an executable environment with pre-installed dependencies, dataset previews, a reference solution, and an automatically synthesized evaluation script. Our evaluation scripts achieve 87.5% agreement with human-annotated gold standards and strong alignment in domain-specific evaluation logic. Training on trajectories sampled from D3-Gym yields consistent gains across Qwen3 models on ScienceAgentBench, boosting Qwen3-32B by 7.8 absolute points and shrinking the gap with strong proprietary models. We further illustrate, through case studies, how D3-Gym environments can serve as a testbed for studying agentic optimization loops such as Autoresearch on real scientific workflows. We open-source D3-Gym, its creation workflow, sampled trajectories, and training scripts at https://github.com/OSU-NLP-Group/D3-Gym.

Hanane Nour Moussa, Yifei Li, Zhuoyang Li +7

1The Ohio State University · 2Cisco Research

AI Agents for Scientific DiscoveryAI Agent BenchmarksSynthetic Benchmark GenerationAutonomous Scientific Discovery
AskPDF
Apr 29, 2026

A self-evolving agent for explainable diagnosis of DFT-experiment band-gap mismatch

Standard density functional theory (DFT) routinely misclassifies the electronic ground state of correlated and structurally complex compounds, predicting metallic behaviour for materials that experiments report as semiconductors. Each such mismatch encodes a specific non-ideality -- magnetic ordering, electron correlation, an alternative polymorph, or a defect -- that the calculation excluded, but extracting that signal at scale has remained a manual exercise. Here we introduce XDFT, a closed-loop agent that diagnoses the mismatch automatically: it draws candidate hypotheses from a curated catalogue, executes the corresponding first-principles tests, and updates a global Bayesian posterior over hypothesis usefulness from each verdict. On a verified benchmark of 124 materials, XDFT identifies a resolving mechanism for 70 of 90 mismatch cases (78%), an order of magnitude above a uniform-random baseline (19%) and a static LLM ordering (20%). The internal posterior aligns with empirical performance over the benchmark timeline, and resolved cases collapse into a tri-partite element-class taxonomy that we distil into a four-line static rule. Each diagnosed material is returned with a corrected protocol and a mechanistic attribution; failed cases are flagged as evidence-backed targets for experimental re-examination.

Yue Li, Bijun Tang

School of Materials Science and Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798.

AI Agents for Scientific DiscoveryMaterials ScienceComputational Materials ScienceDensity Functional Theory
AskPDF
Apr 27, 2026

Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacity has been hindered by the vast complexity gap between scientific discovery and real-world engineering. We introduce SciCrafter, a Minecraft-based benchmark that operationalizes this loop through parameterized redstone circuit tasks. Agents must ignite lamps in specified patterns (e.g., simultaneously or in timed sequences); scaling target parameters substantially increases construction complexity and required knowledge, forcing genuine discovery rather than reliance on memorized solutions. Evaluating frontier models including GPT-5.2, Gemini-3-Pro, and Claude-Opus-4.5 under a general-purpose code agent scaffold, we find that all plateau at approximately 26% success rate. To diagnose these failures, we decompose the loop into four capacities--knowledge gap identification, experimental discovery, knowledge consolidation, and knowledge application--and design targeted interventions whose marginal contributions serve as proxies for corresponding gaps. Our analysis reveals that although the general knowledge application capability still remains as the biggest gap across all models, for frontier models the knowledge gap identification starts to become a major hurdle--indicating the bottleneck is shifting from solving problems right to raising the right problems for current AI. We release SciCrafter as a diagnostic probe for future research on AI systems that navigate the full discovery-to-application loop.

Zhou Ziheng, Huacong Tang, Jinyuan Zhang +9

University of California, Los Angeles · Peking University · Amazon

AI Agents for Scientific DiscoveryCircuit DiscoveryCausal DiscoveryAI Agent Benchmarks
AskPDF
Apr 27, 2026

QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems

We present QED, an open-source multi-agent system that turns human-provided research questions into complete mathematical proofs without further human guidance. Its pipeline is designed to overcome common failures of single-query proof generation by separating planning, proving, and verification: a decomposition agent structures the proof search, prover agents generate candidate arguments, and verifier agents check correctness. In collaboration with domain experts, we evaluated QED on 18 research-level projects of varying difficulty. QED produced five original works across algebraic geometry, fluid PDEs, probability, and inverse problems. Expert assessments regard these works as solid specialized research contributions, with three comparable in difficulty and scope to work commonly published in established specialist mathematics venues. QED is released at https://github.com/proofQED/QED.

Chenyang An, Qihao Ye, Minghao Pan +1

University of California, San Diego, La Jolla, USA · California Institute of Technology, Pasadena, USA · Amazon Web Services

AI Agents for Scientific DiscoveryAutomated Theorem ProvingMulti-Agent ReasoningLLM Mathematical Reasoning
AskPDF
Apr 26, 2026

Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery

Artificial intelligence has accelerated materials discovery through high-throughput prediction and generation, yet the decision problem remains a formidable bottleneck. While current AI systems readily propose millions of candidates, navigating the decision regarding a viable experimental target requires resolving multi-dimensional judgments across atomic-scale numerical computation and high-level semantic reasoning. Here we present ElementsClaw, an agentic framework for materials discovery that orchestrates a suite of Large Atomic Model (LAM) tools finetuned from our proposed 1-billion-parameter model Elements for numerical computation, while leveraging Large Language Models (LLMs) for semantic reasoning. Applied to superconductors, ElementsClaw rediscovers 66 experimentally verified superconductors that are absent from the standard SuperCon3D database. Scaling to 2.4 million equilibrium crystals, ElementsClaw identifies 68,000 high-confidence candidates in just 28 GPU hours (https://developer.damo-academy.com/material), expanding known superconducting space by orders of magnitude compared to datasets curated over decades. Guided by the agent's reasoning, we experimentally synthesize and verify four novel superconductors: the motif-guided Zr3_3ScRe8_8 (TcT_c = 6.5 K), the de novo generated HfZrRe4_4 (TcT_c = 5.9 K), the structurally reinterpreted Zr4_4VRe7_7 (TcT_c = 3.5 K), and the database-latent Hf21_{21}Re25_{25} (TcT_c = 2.5 K). Together, our results establish a knowledge integrated, autonomously orchestrated, and experimentally grounded paradigm for materials discovery.

Mingze Li, Yu Rong, Songyou Li +16

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China. · DAMO Academy, Alibaba Group, Hangzhou, China. · Hupan Lab, Hangzhou, China. +2

AI Agents for Scientific DiscoveryMaterials Property PredictionMaterials ScienceLarge Language Model-Guided Scientific Discovery
AskPDF
Apr 19, 2026

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. However, common agent infrastructure is repeatedly rebuilt across scientific fields (loop fragmentation) and useful evidence and experience are lost in long-horizon research (loop discontinuity), bringing obstacles to Agentic Science at Scale. We introduce EvoMaster, a foundational evolving agent framework for Agentic Science at Scale. EvoMaster handles loop fragmentation and loop discontinuity by implementing Loop Research in which external evidence persists and improves later decisions. Through three nested loops, Execution, Exploration and Evolution (E3^3), loop research connects research within runs, across experiments and across studies. Across ten benchmarks spanning scientific research, coding and reasoning, EvoMaster achieves the best score among four agents using GPT-5.4, reaching a mean score of 58.02%, and outperforms the strongest competing agent Codex(40.29%) while costing 35.6% less. These results show that a shared loop-research foundation can support diverse scientific agents at scale.

Xinyu Zhu, Yuzhu Cai, Zexi Liu +20

School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China. · SciLand, Shanghai, China. · DP Technology, Beijing, China.

Continual Learning for LLM AgentsAI Agents for Scientific DiscoveryAutonomous Research AgentsSelf-Evolving Agents
AskPDF
Apr 18, 2026

ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis

Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science.To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent.

Hao Wang, Jindong Han, Wei Fan +1

1The Hong Kong University of Science and Technology (Guangzhou) · 3Shandong University · University of Auckland +1

AI Agents for Scientific DiscoveryClimate ScienceLLM AgentsLarge Language Model-Guided Scientific Discovery
AskPDF
Apr 17, 2026

Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints

The rise of autonomous AI agents suggests that dynamic benchmark environments with built-in feedback on scientifically grounded tasks are needed to evaluate the capabilities of these agents in research work. We introduce Stargazer, a scalable environment for evaluating AI agents on dynamic, iterative physics-grounded model-fitting tasks using inference on radial-velocity (RV) time series data. Stargazer comprises 120 tasks across three difficulty tiers, including 20 real archival cases, covering diverse scenarios ranging from high-SNR single-planet systems to complex multi-planetary configurations requiring involved low-SNR analysis. Our evaluation of eight frontier agents reveals a gap between numerical optimization and adherence to physical constraints: although agents often achieve a good statistical fit, they frequently fail to recover correct physical system parameters, a limitation that persists even when agents are equipped with vanilla skills. Furthermore, increasing test-time compute yields only marginal gains, with excessive token usage often reflecting recursive failure loops rather than meaningful exploration. Stargazer presents an opportunity to train, evaluate, scaffold, and scale strategies on a model-fitting problem of practical research relevance today. Our methodology to design a simulation-driven environment for AI agents presumably generalizes to many other model-fitting problems across scientific domains. Source code and the project website are available at https://github.com/AIPS-UofT/Stargazer and https://aips-uoft.github.io/Stargazer/, respectively.

Xinge Liu, Terry Jingchen Zhang, Bernhard Schölkopf +2

University of Toronto · 2Vector Institute · 3Max Planck Institute for Intelligent Systems, Tübingen, Germany +1

AI Agents for Scientific DiscoveryAI Agent Benchmarks
AskPDF
Apr 16, 2026

The Agentification of Scientific Research: A Physicist's Perspective

This article argues that the most important significance of the AI revolution, especially the rise of large language models, lies not simply in automation, but in a fundamental change in how complex information and human know-how are carried, replicated, and shared. From this perspective, AI for Science is especially important because it may transform not only the efficiency of research, but also the structure of scientific collaboration, discovery, publishing, and evaluation. The article outlines a gradual path from AI as a research tool to AI as a scientific collaborator, and discusses how AI is likely to fundamentally reshape scientific publication. It also argues that continuous learning and diversity of ideas are essential if AI is to play a meaningful role in original scientific discovery.

Xiao-Liang Qi

Leinweber Institute for Theoretical Physics, Stanford University, Stanford, CA 94305, USA

AI for ScienceAI Agents for Scientific DiscoveryHuman-AI Collaboration
AskPDF
Apr 16, 2026

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data

Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robustness and leakage. The system identified related circadian-instability signals associated with depression, including sleep-duration variability in DWB (ρρ = 0.252, pp < 0.001) and sleep-onset variability in GLOBEM (ρρ = 0.126, pp < 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate; ρρ = -0.374, pp < 0.001). Adding these features to demographic models produced modest gains (ΔR2ΔR^2 = 0.040 for depression, 0.021 for insulin resistance). In a 12-clinician review totaling approximately 25 active hours, clinician validity judgments aligned with CoDaS confidence tiers (ρρ = 0.67, pp = 0.005), whereas added clinical value and confidence to act were rated lower. CoDaS supports traceable, hypothesis-generating prioritization of wearable candidate biomarkers.

Yubin Kim, Salman Rahman, Samuel Schmidgall +33

Google Research · Massachusetts Institute of Technology · Google DeepMind +7

AI Agents for Scientific DiscoveryScientific DiscoveryHuman-in-the-Loop AIWearable Health Monitoring
AskPDF
Apr 15, 2026

MIND: AI Co-Scientist for Material Research

Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental verification. We propose MIND, an LLM-driven framework for automated hypothesis validation in materials research. MIND organizes the scientific discovery process into hypothesis refinement, experimentation, and debate-based validation within a multi-agent pipeline. For experimental verification, the system integrates Machine Learning Interatomic Potentials, particularly SevenNet-Omni, enabling scalable in-silico experiments. We also provide a web-based user interface for automated hypothesis testing. The modular design allows additional experimental modules to be integrated, making the framework adaptable to broader scientific workflows. The code is available at: https://github.com/IMMS-Ewha/MIND, and a demonstration video at: https://youtu.be/lqiFe1OQzN4.

Geonhee Ahn, Donghyun Lee, Hayoung Doo +3

Institute for Multiscale Matter and Systems (IMMS), Ewha Womans University, Seoul 03760, Republic of Korea

AI Agents for Scientific DiscoveryAutonomous ExperimentationMaterials ScienceMulti-Agent LLM Systems
AskPDF