mlsanityData to 7 Oct 2026

SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning

arXiv 2409.05556 ↗First posted 9 Sep 2024cs.AI cond-mat.dis-nn cond-mat.mtrl-scicited by 90

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to biologically inspired materials, SciAgents reveals hidden interdisciplinary relationships that were previously considered unrelated, achieving a scale, precision, and exploratory power that surpasses traditional human-driven research methods. The framework autonomously generates and refines research hypotheses, elucidating underlying mechanisms, design principles, and unexpected material properties. By integrating these capabilities in a modular fashion, the intelligent system yields material discoveries, critique and improve existing hypotheses, retrieve up-to-date data about existing research, and highlights their strengths and limitations. Our case studies demonstrate scalable capabilities to combine generative AI, ontological representations, and multi-agent modeling, harnessing a `swarm of intelligence' similar to biological systems. This provides new avenues for materials discovery and accelerates the development of advanced materials by unlocking Nature's design principles.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 15 of its 46 references that are in the map. First posted on arXiv 9 Sep 2024.

Builds on

15 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph15 Jul

Other references · 14

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Mistral 7Bcited by 3,065
  4. 2023A Survey of Large Language Modelscited by 2,537
  5. 2022Emergent Abilities of Large Language Modelscited by 2,483
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  7. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  8. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  9. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
  10. 2023Textbooks Are All You Needcited by 561
  11. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 67
  12. 2024Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilitiescited by 67
2 more
  1. 2024AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligencecited by 36
  2. 2024From Text to Insight: Large Language Models for Materials Science Data Extractioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 43; 2026: 34.

90 papers.

Sort:

By area:

  1. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  2. 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systemscited by 170
  3. 2025DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Processcited by 97
  4. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 96
  5. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 94
  6. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 86
  7. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directionscited by 74
  8. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  9. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64
  10. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 58
  11. 2025SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writingcited by 47
  12. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflowscited by 47
38 more
  1. 2024Project Sid: Many-agent simulations toward AI civilizationcited by 46
  2. 2025SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Paperscited by 42
  3. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challengescited by 41
  4. 2025Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysiscited by 33
  5. 2025Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agentscited by 31
  6. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agentscited by 30
  7. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 25
  8. 2024LLM-based Multi-Agent Systems: Techniques and Business Perspectivescited by 22
  9. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 20
  10. 2024Literature Meets Data: A Synergistic Approach to Hypothesis Generationcited by 19
  11. 2024PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinkingcited by 17
  12. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  13. 2025Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systemscited by 14
  14. 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvementcited by 13
  15. 2025AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentationcited by 13
  16. 2024EcoAct: Economic Agent Determines When to Register What Actioncited by 11
  17. 2025In-situ graph reasoning and knowledge expansion using Graph-PReFLexORcited by 11
  18. 2025SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPscited by 11
  19. 2025How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?cited by 10
  20. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  21. 2025A Survey of AI Scientistscited by 9
  22. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  23. 2025Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automationcited by 8
  24. 2024Creativity in AI: Progresses and Challengescited by 7
  25. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  26. 2024Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systemscited by 6
  27. 2025Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformerscited by 6
  28. 2025PriM: Principle-Inspired Material Discovery through Multi-Agent Collaborationcited by 6
  29. 2025XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaborationcited by 6
  30. 2025URSA: The Universal Research and Scientific Agentcited by 6
  31. 2025Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstructioncited by 6
  32. 2026SciFig: Towards Automating Editable Figure Generation for Scientific Paperscited by 6
  33. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  34. 2024EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agentcited by 4
  35. 2025Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directionscited by 4
  36. 2026A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archivescited by 4
  37. 2026SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Promptscited by 4
  38. 2025AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Researchcited by 3

50 most cited of 90 All 90 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design
  2. 2025SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
  3. 2026AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
  4. 2025SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
  5. 2026Higher-Order Knowledge Representations for Agentic Scientific Reasoning
  6. 2026AutoKD: Autonomous Knowledge Discovery
  7. 2026SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
  8. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics