mlsanityData to 14 Oct 2026

Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions

arXiv 2503.08979 ↗First posted 12 Mar 2025cs.CLcited by 77

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

Abstract (arXiv)

The integration of Agentic AI into scientific discovery marks a new frontier in research automation. These AI systems, capable of reasoning, planning, and autonomous decision-making, are transforming how scientists perform literature review, generate hypotheses, conduct experiments, and analyze results. This survey provides a comprehensive overview of Agentic AI for scientific discovery, categorizing existing systems and tools, and highlighting recent progress across fields such as chemistry, biology, and materials science. We discuss key evaluation metrics, implementation frameworks, and commonly used datasets to offer a detailed understanding of the current state of the field. Finally, we address critical challenges, such as literature review automation, system reliability, and ethical concerns, while outlining future research directions that emphasize human-AI collaboration and enhanced system calibration.

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 54 of its 78 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

54 of 78 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Agent Laboratory: Using LLM Agents as Research Assistants8 Jan
  2. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering9 Oct
  3. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning9 Sep
  4. 2024MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents26 Aug
  5. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation5 Oct
  6. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul
  7. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun

Other references · 47

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  7. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  8. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  9. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  10. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  11. 2022Galactica: A Large Language Model for Sciencecited by 744
  12. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
35 more
  1. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  2. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 255
  3. 2024AI Agents That Mattercited by 219
  4. 2023HuatuoGPT, towards Taming Language Model to Be a Doctorcited by 214
  5. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
  6. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  7. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 160
  8. 2024LAB-Bench: Measuring Capabilities of Language Models for Biology Researchcited by 156
  9. 2023Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Modelscited by 133
  10. 2024Empowering Biomedical Discovery with AI Agentscited by 118
  11. 2023Large Language Models for Automated Open-domain Scientific Hypotheses Discoverycited by 100
  12. 2023Conversational Health Agents: A Personalized LLM-Powered Agent Frameworkcited by 92
  13. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
  14. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 72
  15. 2023Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4cited by 68
  16. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learningcited by 64
  17. 2024ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterizationcited by 61
  18. 2024CRISPR-GPT for Agentic Automation of Gene-editing Experimentscited by 58
  19. 2024LitSearch: A Retrieval Benchmark for Scientific Literature Searchcited by 50
  20. 2024CiteME: Can Language Models Accurately Cite Scientific Claims?cited by 48
  21. 2023Large Language Models are Zero Shot Hypothesis Proposerscited by 45
  22. 2023BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biologycited by 43
  23. 2024CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysiscited by 39
  24. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 36
  25. 2023MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modelingcited by 35
  26. 2024LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillationcited by 32
  27. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agentscited by 30
  28. 2024SciLitLLM: How to Adapt LLMs for Scientific Literature Understandingcited by 29
  29. 2023Opportunities for Retrieval and Tool Augmented Large Language Models in Scientific Facilitiescited by 27
  30. 2023ChatMOF: An Autonomous AI System for Predicting and Generating Metal-Organic Frameworkscited by 17
  31. 2024Less can be more for predicting properties with large language modelscited by 11
  32. 2024MatPilot: an LLM-enabled AI Materials Scientist under the Framework of Human-Machine Collaborationcited by 11
  33. 2024Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Datacited by 10
  34. 2024Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfittingcited by 6
  35. 2024Building Living Software Systems with Generative & Agentic AIcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 41; 2026: 36.

77 papers.

Sort:

By area:

  1. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 169
  3. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149
  4. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  5. 2025ExGRPO: Learning to Reason from Experiencecited by 53
  6. 2026EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discoverycited by 51
  7. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 48
  8. 2025SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Paperscited by 43
  9. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 33
  10. 2025ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquirycited by 32
  11. 2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 30
  12. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 28
38 more
  1. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 28
  2. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 26
  3. 2025How Far Are AI Scientists from Changing the World?cited by 15
  4. 2025AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentationcited by 15
  5. 2025CoDA: Agentic Systems for Collaborative Data Visualizationcited by 15
  6. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
  7. 2025Can Language Models Discover Scaling Laws?cited by 13
  8. 2025Automating MD simulations for Proteins using Large language Models: NAMD-Agentcited by 12
  9. 2026Benchmarking AI Agents for Addressing Scientific Challenges Across Scalescited by 12
  10. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  11. 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agentscited by 10
  12. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 10
  13. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 9
  14. 2025The Need for Verification in AI-Driven Scientific Discoverycited by 7
  15. 2025Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AIcited by 7
  16. 2026Principle-Evolvable Scientific Discovery via Uncertainty Minimizationcited by 7
  17. 2025URSA: The Universal Research and Scientific Agentcited by 6
  18. 2025From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Modelscited by 5
  19. 2026A Practical Guide to Agentic AI Transition in Organizationscited by 5
  20. 2026Mozi: Governed Autonomy for Drug Discovery LLM Agentscited by 5
  21. 2026The Path Ahead for Agentic AI: Challenges and Opportunitiescited by 4
  22. 2026SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discoverycited by 4
  23. 2025Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflowscited by 3
  24. 2025Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challengescited by 3
  25. 2025A Hierarchical Agentic Framework for Autonomous Drone-Based Visual Inspectioncited by 3
  26. 2025GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agentscited by 3
  27. 2026EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Designcited by 3
  28. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communicationscited by 2
  29. 2025AutoPR: Let's Automate Your Academic Promotion!cited by 2
  30. 2025ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulationscited by 2
  31. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  32. 2025Socio-technical aspects of Agentic AIcited by 2
  33. 2026BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigationcited by 2
  34. 2026Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaborationcited by 2
  35. 2026ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgmentcited by 2
  36. 2025Counting Cycles with AI: Counting Cycles with AI: Computationally Efficient Equivalent Forms with Applicationscited by 1
  37. 2025Risk-Sensitive Agent Compositionscited by 1
  38. 2025Steering Conceptual Bias via Transformer Latent-Subspace Activationcited by 1

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
  2. 2025AI Agents in Drug Discovery
  3. 2025Virtuous Machines: Towards Artificial General Science
  4. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges
  5. 2025AI-Researcher: Autonomous Scientific Innovation
  6. 2026AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions
  7. 2026Towards Agentic Intelligence for Materials Science
  8. 2026Towards End-to-End Automation of AI Research