M3OS：一种蒙特卡洛图搜索编排的多智能体LLM系统，用于证据追踪的分子优化
M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
查看机构详情
- Lingang Laboratory（临港实验室）
- ShanghaiTech University（上海科技大学）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
M3OS通过蒙特卡洛图搜索解耦分子设计推理与状态管理，结合多智能体协作和受控执行，在三个基准上实现更高成功率，用于多约束分子优化。
中文摘要 AI 辅助
小分子优化通过迭代的多目标决策，整合了药物化学推理与计算证据。当大型语言模型（LLMs）主要在对话上下文中存储的优化历史进行推理时，它们必须恢复候选身份、先前评估和任务约束以指导后续决策。我们提出了M3OS，一种多智能体LLM系统，通过蒙特卡洛图搜索将分子设计推理与优化状态管理解耦。一个持久化图连接了已评估的候选、父子变换和评估证据，而奖励和访问统计指导LLM辅助的父节点选择。两个分支结合了工具驱动的候选生成与知识和案例引导的药物化学编辑。一个执行框架通过结构化输出提取、分子验证和任务约束评估来控制图更新。智能体接收角色特定的上下文，而图在其活动上下文之外保留优化轨迹。在三个分子优化基准上，M3OS实现了比基线更高的成功率，支持将持久搜索状态、专门智能体和受控执行集成用于多约束优化。
英文摘要
Small-molecule optimization integrates medicinal-chemistry reasoning and computational evidence through iterative, multi-objective decisions. When large language models (LLMs) reason over optimization histories stored primarily in conversational context, they must recover candidate identities, prior evaluations, and task constraints to guide subsequent decisions. We present M3OS, a multi-agent LLM system that decouples molecular-design reasoning from optimization-state management through Monte Carlo graph search. A persistent graph links evaluated candidates, parent-child transformations and evaluation evidence, while rewards and visit statistics guide LLM-assisted parent selection. Two branches combine tool-driven candidate generation with knowledge- and case-guided medicinal-chemistry editing. An execution harness controls graph updates through structured output extraction, molecular validation and task-bound evaluation. Agents receive role-specific contexts, while the graph preserves optimization trajectories beyond their active contexts. Across three molecular optimization benchmarks, M3OS achieves higher success rates than baselines, supporting the integration of persistent search state, specialized agents and controlled execution for multi-constraint optimization.
