mlsanityData to 7 Oct 2026

Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents

arXiv 2501.13299 ↗First posted 23 Jan 2025cs.CLcited by 30

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Materials discovery and design are essential for advancing technology across various industries by enabling the development of application-specific materials. Recent research has leveraged Large Language Models (LLMs) to accelerate this process. We explore the potential of LLMs to generate viable hypotheses that, once validated, can expedite materials discovery. Collaborating with materials science experts, we curated a novel dataset from recent journal publications, featuring real-world goals, constraints, and methods for designing real-world applications. Using this dataset, we test LLM-based agents that generate hypotheses for achieving given goals under specific constraints. To assess the relevance and quality of these hypotheses, we propose a novel scalable evaluation metric that emulates the process a materials scientist would use to evaluate a hypothesis critically. Our curated dataset, proposed method, and evaluation framework aim to advance future research in accelerating materials discovery and design with LLMs.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 40 references that are in the map. First posted on arXiv 23 Jan 2025.

Builds on

17 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024HoneyComb: A Flexible LLM-Based Agent System for Materials Science29 Aug

Other references · 16

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  2. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  4. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  5. 2022Galactica: A Large Language Model for Sciencecited by 736
  6. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  7. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 179
  8. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  9. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoningcited by 90
  10. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 68
  11. 2020An invertible crystallographic representation for general inverse design of inorganic crystals with targeted propertiescited by 53
  12. 2024ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedbackcited by 32
4 more
  1. 2023HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Sciencecited by 22
  2. 2024MatExpert: Decomposing Materials Discovery by Mimicking Human Expertscited by 18
  3. 2024SmileyLlama: Modifying Large Language Models for Directed Chemical Space Explorationcited by 14
  4. 2022Scientific Paper Extractive Summarization Enhanced by Citation Graphscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 13.

30 papers.

Sort:

By area:

  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  2. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directionscited by 74
  3. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  4. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  6. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  7. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 25
  8. 2025Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidationcited by 17
  9. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  10. 2025LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discoverycited by 11
  11. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  12. 2025PriM: Principle-Inspired Material Discovery through Multi-Agent Collaborationcited by 6
18 more
  1. 2025GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Timecited by 5
  2. 2026TritonDFT: Automating DFT with a Multi-Agent Frameworkcited by 5
  3. 2026FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environmentscited by 4
  4. 2025BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis Generationcited by 3
  5. 2026Towards Agentic Intelligence for Materials Sciencecited by 3
  6. 2025Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judgecited by 2
  7. 2026Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Frameworkcited by 2
  8. 2025Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimizationcited by 1
  9. 2025GeoEvolve: Automating Geospatial Model Discovery via Multi-Agent Large Language Modelscited by 1
  10. 2026Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientistscited by 1
  11. 2026COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learningcited by 1
  12. 2025OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulationcited by 0
  13. 2026Full-Stack Domain Enhancement for Combustion LLMs: Construction and Optimizationcited by 0
  14. 2026SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applicationscited by 0
  15. 2026The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?cited by 0
  16. 2026Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generationcited by 0
  17. 2026MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistrycited by 0
  18. 2026HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledgecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Are LLMs Ready for Real-World Materials Discovery?
  2. 2025Large language models in materials science and the need for open-source approaches
  3. 2024LLMatDesign: Autonomous Materials Discovery with Large Language Models
  4. 2025A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools
  5. 2025LLM Agents for Knowledge Discovery in Atomic Layer Processing
  6. 2025Role of Large Language Models and Retrieval-Augmented Generation for Accelerating Crystalline Material Discovery: A Systematic Review
  7. 202534 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery
  8. 2026Evaluating LLM-based AI agents integrated with materials synthesis tools: the case of atomic layer deposition