CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning

2025/06/09 by Mengsong Wu, Wu, Mengsong, Yafei Wang +17 · 1 citation
Computer Science · Materials Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Chemical space #Code (set theory) #Computation and Language (cs.CL) #Computational Drug Discovery Methods #Computational Engineering #FOS: Computer and information sciences #Finance #Machine Learning (cs.LG) #Machine Learning in Materials Science #Pipeline (software) #Tree (set theory) #and Science (cs.CE)

paper · pdf · doi:10.48550/arxiv.2506.07551

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/06/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks while still facing challenges due to outdated pretraining knowledge and the difficulty of incorporating specialized chemical expertise. To address these issues, we propose an LLM-based agent that synergistically integrates 137 external chemical tools created ranging from basic information retrieval to complex reaction predictions, and a dataset curation pipeline to generate the dataset ChemToolBench that facilitates both effective tool selection and precise parameter filling during fine-tuning and evaluation. We introduce a Hierarchical Evolutionary Monte Carlo Tree Search (HE-MCTS) framework, enabling independent optimization of tool planning and execution. By leveraging self-generated data, our approach supports step-level fine-tuning (FT) of the policy model and training task-adaptive PRM and ORM that surpass GPT-4o. Experimental evaluations demonstrate that our approach significantly improves performance in Chemistry QA and discovery tasks, offering a robust solution to integrate specialized tools with LLMs for advanced chemical applications. All datasets and code are available at https://github.com/AI4Chem/ChemistryAgent .

Citations

• ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback
• ToolACE: Winning the Points of LLM Function Calling
• Step-level Value Preference Optimization for Mathematical Reasoning
• Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
• Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
• ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
• Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark
• AlphaMath Almost Zero: Process Supervision without Process
• Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
• Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
• Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
• Counterfactually Auditable Lifecycle Certification for Autonomous Agents
• ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
• API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
• Toolformer: Language Models Can Teach Themselves to Use Tools
• An Algorithm for Fast Recovery of Sparse Causal Graphs

Cited by

• AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation

Related

• ChemHTS: Hierarchical Tool Stacking for Enhancing Chemical Agents
• LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset
• ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions
• ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving
• Developing ChemDFM as a large language foundation model for chemistry