用多个专家智能体协同优化分子，提升可解释性与性能。
MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization
- 分角色智能体协作，各司其职处理化学工具
- 在PMO-1K基准上17/23任务达最先进水平
- 适合药物研发与分子设计领域研究人员
大型语言模型（LLMs）在分子优化中具有巨大潜力，可通过调用外部化学工具并实现协同交互，迭代优化分子候选。然而，这一潜力尚未被充分挖掘，尤其是在结构化推理、可解释性及全面的工具驱动优化方面。为此，我们提出MT-Mol，一个基于工具引导推理的角色专业化多智能体框架。系统整合了五类完整的RDKit工具：结构描述符、电子与拓扑特征、片段功能基团、分子表示及其它化学性质。每类由专门的分析代理负责，提取任务相关工具并提供可解释的化学反馈。通过分析代理、分子生成科学家、推理输出验证器和评审代理之间的交互，MT-Mol实现了工具对齐、逐步推理的分子生成。实验表明，该框架在PMO-1K基准的23项任务中，有17项达到当前最优表现。
原文摘要 · Abstract (English)
Large language models (LLMs) have large potential for molecular optimization, as they can gather external chemistry tools and enable collaborative interactions to iteratively refine molecular candidates. However, this potential remains underexplored, particularly in the context of structured reasoning, interpretability, and comprehensive tool-grounded molecular optimization. To address this gap, we introduce MT-Mol, a multi-agent framework for molecular optimization that leverages tool-guided reasoning and role-specialized LLM agents. Our system incorporates comprehensive RDKit tools, categorized into five distinct domains: structural descriptors, electronic and topological features, fragment-based functional groups, molecular representations, and miscellaneous chemical properties. Each category is managed by an expert analyst agent, responsible for extracting task-relevant tools and enabling interpretable, chemically grounded feedback. MT-Mol produces molecules with tool-aligned and stepwise reasoning through the interaction between the analyst agents, a molecule-generating scientist, a reasoning-output verifier, and a reviewer agent. As a result, we show that our framework shows the state-of-the-art performance of the PMO-1K benchmark on 17 out of 23 tasks.
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。