mlsanityData to 14 Oct 2026

Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

arXiv 2510.09901 ↗First posted 10 Oct 2025cs.AIcited by 11

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accelerate discovery across varying levels of autonomy. These language agents provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics. This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle, from hypothesis discovery, experimental design and execution, to result analysis and refinement. We critically examine current methodologies, emphasizing key innovations, practical achievements, and outstanding limitations. Additionally, we identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents. Our analysis highlights the transformative potential of autonomous agents to accelerate scientific discovery across diverse domains.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 149 of its 250 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

149 of 250 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery18 Aug
  2. 2025Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimization3 Aug
  3. 2025SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration27 Jul
  4. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning22 May
  5. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search10 Apr
  6. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents31 Mar
  7. 2025AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data29 Mar
  8. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions12 Mar
  9. 2025Automated Hypothesis Validation with Agentic Sequential Falsifications14 Feb
  10. 2024Agents for self-driving laboratories applied to quantum computing10 Dec
  11. 2024Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System12 Oct
  12. 2024MetaOpenFOAM: an LLM-based multi-agent framework for CFD31 Jul
1 more
  1. 2024Data Interpreter: An LLM Agent For Data Science28 Feb

Other references · 136

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  9. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  10. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  11. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  12. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
38 more
  1. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  3. 2023Teaching Large Language Models to Self-Debugcited by 988
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  5. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  6. 2023Large Language Modelscited by 780
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  8. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  9. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  10. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  11. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
  12. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  13. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  14. 2024Understanding the planning of LLM agents: A surveycited by 421
  15. 2023Augmented Language Models: a Surveycited by 403
  16. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  17. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  18. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 335
  19. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  20. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 285
  21. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 265
  22. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
  23. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 187
  24. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 179
  25. 2025ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolutioncited by 174
  26. 2023ChartLlama: A Multimodal LLM for Chart Understanding and Generationcited by 163
  27. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learningcited by 161
  28. 2025RM-R1: Reward Modeling as Reasoningcited by 154
  29. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  30. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcited by 136
  31. 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behaviorcited by 131
  32. 2023Large Language Models as Evolutionary Optimizerscited by 124
  33. 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 124
  34. 2023Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systemscited by 121
  35. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 119
  36. 2024Empowering Biomedical Discovery with AI Agentscited by 118
  37. 2024LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Modelscited by 99
  38. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96

50 most cited of 136 All 136 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2025AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learningcited by 14
  2. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 10
  3. 2026AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generationcited by 2
  4. 2026TianJi:An autonomous AI meteorologist for discovering physical mechanisms in atmospheric sciencecited by 2
  5. 2026AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculationscited by 2
  6. 2025Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecturecited by 1
  7. 2026Democratizing and accelerating AI-driven pathology research through agentic intelligencecited by 1
  8. 2026More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideationcited by 0
  9. 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspectivecited by 0
  10. 2026Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systemscited by 0
  11. 2026Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasetscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AI-Researcher: Autonomous Scientific Innovation
  2. 2025Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
  3. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
  4. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
  5. 2026AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding
  6. 2026Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
  7. 2023Emergent autonomous scientific research capabilities of large language models
  8. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery