用树搜索整合137个化学工具，让大模型更懂材料科学。
CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning
- 通过分层蒙特卡洛树搜索优化工具选择与执行策略。
- 在化学问答和发现任务中性能超越GPT-4o，提升显著。
- 适合需要精准化学推理的科研人员与工业研发团队。
大语言模型在化学任务中展现出潜力，但仍受限于过时的预训练知识及难以融入专业化学知识。为此，我们提出一个基于LLM的智能体，协同集成137个外部化学工具（涵盖信息检索到反应预测），并构建数据集生成管道，创建ChemToolBench数据集，以支持细粒度工具选择与参数填充的微调与评估。引入分层进化蒙特卡洛树搜索（HE-MCTS）框架，实现工具规划与执行的独立优化。利用自生成数据，支持策略模型的步骤级微调，并训练任务自适应的PRM与ORM，其性能超越GPT-4o。实验表明，该方法在化学问答与发现任务中表现优异，为大模型融合专业工具提供了可靠方案。所有数据与代码开源：https://github.com/AI4Chem/ChemistryAgent。
原文摘要 · Abstract (English)
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models (LLMs) have recently demonstrated promising capabilities in chemistry tasks while still facing challenges due to outdated pretraining knowledge and the difficulty of incorporating specialized chemical expertise.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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。