mlsanityData to 14 Oct 2026

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

arXiv 2508.14111 ↗First posted 18 Aug 2025cs.LGcited by 77

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

Abstract (arXiv)

Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within the broader AI for Science paradigm, where AI systems progress from partial assistance to full scientific agency. Enabled by large language models (LLMs), multimodal systems, and integrated research platforms, agentic AI shows capabilities in hypothesis generation, experimental design, execution, analysis, and iterative refinement -- behaviors once regarded as uniquely human. This survey provides a domain-oriented review of autonomous scientific discovery across life sciences, chemistry, materials science, and physics. We unify three previously fragmented perspectives -- process-oriented, autonomy-oriented, and mechanism-oriented -- through a comprehensive framework that connects foundational capabilities, core processes, and domain-specific realizations. Building on this framework, we (i) trace the evolution of AI for Science, (ii) identify five core capabilities underpinning scientific agency, (iii) model discovery as a dynamic four-stage workflow, (iv) review applications across the above domains, and (v) synthesize key challenges and future opportunities. This work establishes a domain-oriented synthesis of autonomous scientific discovery and positions Agentic Science as a structured paradigm for advancing AI-driven research.

Key facts. Cited by 77 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 250 of its 455 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

250 of 455 references.

Closest ancestors · 23

Same direction, newest first

  1. 2025Bridging Literature and the Universe Via A Multi-Agent Large Language Model System11 Jul
  2. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration21 May
  3. 2025Empowering Scientific Workflows with Federated Agents8 May
  4. 2025Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows8 May
  5. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search10 Apr
  6. 2025The AI Cosmologist I: An Agentic System for Automated Data Analysis4 Apr
  7. 2025Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning2 Apr
  8. 2025SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers31 Mar
  9. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents31 Mar
  10. 2025AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data29 Mar
  11. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions12 Mar
  12. 2025AI Agents for Ground-Based Gamma Astronomy2 Mar
11 more
  1. 2025Agent Laboratory: Using LLM Agents as Research Assistants8 Jan
  2. 2024Agents for self-driving laboratories applied to quantum computing10 Dec
  3. 2024Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents1 Dec
  4. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering9 Oct
  5. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning9 Sep
  6. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers6 Sep
  7. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning27 Feb
  8. 2024SciAgent: Tool-augmented Language Models for Scientific Reasoning18 Feb
  9. 2024Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate12 Feb
  10. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning10 Jan
  11. 2023Controlling risks of AI in chemical science with agents11 Dec

Other references · 227

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  6. 2023Qwen Technical Reportcited by 3,344
  7. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  10. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  11. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  12. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
38 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  2. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  3. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  4. 2022Galactica: A Large Language Model for Sciencecited by 744
  5. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  6. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  7. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
  8. 2025MedGemma Technical Reportcited by 436
  9. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  10. 2024Understanding the planning of LLM agents: A surveycited by 421
  11. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  12. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 392
  13. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 384
  14. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  15. 2023MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Datacited by 286
  16. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 282
  17. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  18. 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMscited by 265
  19. 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMscited by 234
  20. 2025AIDE: AI-Driven Exploration in the Space of Codecited by 226
  21. 2023Large Language Model Guided Tree-of-Thoughtcited by 221
  22. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
  23. 2024V-STaR: Training Verifiers for Self-Taught Reasonerscited by 217
  24. 2023HuatuoGPT, towards Taming Language Model to Be a Doctorcited by 214
  25. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
  26. 2025Survey on Evaluation of LLM-based Agentscited by 204
  27. 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scalecited by 200
  28. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  29. 2024SciCode: A Research Coding Benchmark Curated by Scientistscited by 178
  30. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  31. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 168
  32. 2020Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claimscited by 165
  33. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)cited by 159
  34. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 159
  35. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 154
  36. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  37. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  38. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126

50 most cited of 227 All 227 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 17; 2026: 60.

77 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2026SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resourcescited by 41
  3. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  4. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 36
  5. 2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 30
  6. 2025TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysiscited by 22
  7. 2026SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agentscited by 15
  8. 2026Policy and World Modeling Co-Training for Language Agentscited by 15
  9. 2025AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learningcited by 14
  10. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 14
  11. 2026LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Taskscited by 13
  12. 2025PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMscited by 11
38 more
  1. 2025SciReasoner: Laying the Scientific Reasoning Ground Across Disciplinescited by 11
  2. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  3. 2025A Survey of AI Scientistscited by 11
  4. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 10
  5. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 9
  6. 2026El Agente Quntur: A research collaborator agent for quantum chemistrycited by 8
  7. 2026Principle-Evolvable Scientific Discovery via Uncertainty Minimizationcited by 7
  8. 2026QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilitiescited by 6
  9. 2026When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoningcited by 5
  10. 2026A Definition and Roadmap for World Modelscited by 5
  11. 2026SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discoverycited by 4
  12. 2026El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agentscited by 4
  13. 2026Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstructioncited by 4
  14. 2026HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shiftscited by 4
  15. 2026Towards LLM-enabled autonomous combustion research: A literature-aware agent for self-corrective modeling workflowscited by 3
  16. 2026The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordinationcited by 3
  17. 2026ConvexBench: Can LLMs Recognize Convex Functions?cited by 3
  18. 2025AutoPR: Let's Automate Your Academic Promotion!cited by 2
  19. 2025AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.orgcited by 2
  20. 2025Socio-technical aspects of Agentic AIcited by 2
  21. 2026Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideationcited by 2
  22. 2026Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agentscited by 2
  23. 2026Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflowscited by 2
  24. 2026AgentTrails: Towards Trust and Reuse for Agentic Taskscited by 2
  25. 2025Bidirectional Representations Augmented Autoregressive Biological Sequence Generationcited by 1
  26. 2025Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecturecited by 1
  27. 2026Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMscited by 1
  28. 2026Embodied Science: Closing the Discovery Loop with Agentic Embodied AIcited by 1
  29. 2026Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Sciencecited by 1
  30. 2026Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Researchcited by 1
  31. 2026Competing with AI Scientists: Agent-Driven Approach to Astrophysics Researchcited by 1
  32. 2026Heterogeneous Scientific Foundation Model Collaborationcited by 1
  33. 2026Hypothesis generation and updating in large language modelscited by 1
  34. 2026DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discoverycited by 1
  35. 2026Workflow Closure Is Not Scientific Closure in Auto-Research Systemscited by 1
  36. 2026Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientistcited by 1
  37. 2026Scientific discovery as meta-optimization: a combinatorial optimization case studycited by 1
  38. 2026Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systemscited by 1

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Virtuous Machines: Towards Artificial General Science
  2. 2025AI-Researcher: Autonomous Scientific Innovation
  3. 2026AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions
  4. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges
  5. 2026Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
  6. 2025Scaling Laws in Scientific Discovery with AI and Robot Scientists
  7. 2025AI Agents in Drug Discovery
  8. 2025Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models