mlsanityData to 7 Oct 2026

HoneyComb: A Flexible LLM-Based Agent System for Materials Science

arXiv 2409.00135 ↗First posted 29 Aug 2024cs.CL cs.AIcited by 56

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

Abstract (arXiv)

The emergence of specialized large language models (LLMs) has shown promise in addressing complex tasks for materials science. Many LLMs, however, often struggle with distinct complexities of material science tasks, such as materials science computational tasks, and often rely heavily on outdated implicit knowledge, leading to inaccuracies and hallucinations. To address these challenges, we introduce HoneyComb, the first LLM-based agent system specifically designed for materials science. HoneyComb leverages a novel, high-quality materials science knowledge base (MatSciKB) and a sophisticated tool hub (ToolHub) to enhance its reasoning and computational capabilities tailored to materials science. MatSciKB is a curated, structured knowledge collection based on reliable literature, while ToolHub employs an Inductive Tool Construction method to generate, decompose, and refine API tools for materials science. Additionally, HoneyComb leverages a retriever module that adaptively selects the appropriate knowledge source or tools for specific tasks, thereby ensuring accuracy and relevance. Our results demonstrate that HoneyComb significantly outperforms baseline models across various tasks in materials science, effectively bridging the gap between current LLM capabilities and the specialized needs of this domain. Furthermore, our adaptable framework can be easily extended to other scientific domains, highlighting its potential for broad applicability in advancing scientific research and applications.

Key facts. Cited by 56 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 22 of its 43 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

22 of 43 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  8. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  9. 2017Crowdsourcing Multiple Choice Science Questionscited by 742
  10. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  11. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  12. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
10 more
  1. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 130
  2. 2023SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Researchcited by 112
  3. 2023The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4cited by 112
  4. 202314 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathoncited by 85
  5. 2024Are LLMs Ready for Real-World Materials Discovery?cited by 40
  6. 2023MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalitiescited by 38
  7. 2023MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modelingcited by 35
  8. 2024Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agentscited by 35
  9. 2023Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPTcited by 29
  10. 2023HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Sciencecited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 33; 2026: 16.

56 papers.

Sort:

By area:

  1. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  2. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  3. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  4. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 96
  5. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  6. 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 65
  7. 2025ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agentscited by 64
  8. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  9. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agentscited by 30
  10. 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysiscited by 28
  11. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 25
  12. 2024MatExpert: Decomposing Materials Discovery by Mimicking Human Expertscited by 18
38 more
  1. 2024Foundational Large Language Models for Materials Researchcited by 18
  2. 2025Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAMcited by 15
  3. 2025MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Sciencecited by 15
  4. 2025The AI Agent Indexcited by 14
  5. 2025DeepSeek vs. ChatGPT vs. Claude: A Comparative Study for Scientific Computing and Scientific Machine Learning Taskscited by 12
  6. 2026Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoningcited by 12
  7. 2026ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methodscited by 12
  8. 2025MatTools: Benchmarking Large Language Models for Materials Science Toolscited by 11
  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. 2024AI-driven inverse design of materials: Past, present and futurecited by 10
  12. 202534 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discoverycited by 9
  13. 2024Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistrycited by 8
  14. 2024MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Designcited by 8
  15. 2025Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterizationcited by 8
  16. 2025A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Toolscited by 7
  17. 2025PriM: Principle-Inspired Material Discovery through Multi-Agent Collaborationcited by 6
  18. 2026MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamicscited by 6
  19. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  20. 2026Pancake: Hierarchical Memory System for Multi-Agent LLM Servingcited by 5
  21. 2026TritonDFT: Automating DFT with a Multi-Agent Frameworkcited by 5
  22. 2025Stress-Testing Multimodal Foundation Models for Crystallographic Reasoningcited by 4
  23. 2025IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectracited by 4
  24. 2025VASP Agent: An Agentic Framework for Autonomous First-principles Calculationscited by 4
  25. 2025ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructionscited by 3
  26. 2026M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraintscited by 3
  27. 2025Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Researchcited by 2
  28. 2026S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Researchcited by 2
  29. 2026IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Reviewcited by 2
  30. 2025Beyond Atomic Geometry Representations in Materials Science: A Human-in-the-Loop Multimodal Frameworkcited by 1
  31. 2025Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental designcited by 1
  32. 2025AISSISTANT: Human-AI Collaborative Review and Perspective Research Workflows in Data Sciencecited by 1
  33. 2025LLM Agents for Knowledge Discovery in Atomic Layer Processingcited by 1
  34. 2025ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literaturecited by 1
  35. 2026An Alternative Trajectory for Generative AIcited by 1
  36. 2026SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Sciencecited by 1
  37. 2026REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinementcited by 1
  38. 2025Preface to the Special Issue of the TAL Journal on Scholarly Document Processingcited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Large language models in materials science and the need for open-source approaches
  2. 2026From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry
  3. 2026Towards Agentic Intelligence for Materials Science
  4. 2024LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation
  5. 2026From Data to Theory: Autonomous Large Language Model Agents for Materials Science
  6. 2026Evaluating LLM-based AI agents integrated with materials synthesis tools: the case of atomic layer deposition
  7. 2025AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials
  8. 2026GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design