用结构化记忆增强LLM，实现更智能的逆合成路径规划
RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
- 构建带结构化记忆的LLM代理，全局感知搜索状态
- 在分布内与分布外测试中均表现优异，泛化能力强
- 适合药物研发、自动化合成设计等场景
多步逆合成规划旨在通过一系列可行反应，将目标分子分解为可购得的原料。庞大的组合搜索空间使该任务即使对专家也极具挑战。传统方法结合树搜索与离线训练的价值网络，仅孤立评分候选物，缺乏对完整多步路径的推理。近期工作虽利用大语言模型（LLMs）处理此任务，但依赖简单接口，限制了搜索空间探索。我们提出RetroAgent，一个通过结构化记忆连接符号搜索与神经推理的LLM代理。借助记忆与化学工具，代理可观察完整搜索状态，包括已探索路径、可用替代方案及中间体属性，从而基于全局进展与领域知识做出明智决策。在分布内与分布外基准测试中，RetroAgent展现出强劲性能与良好泛化能力。
原文摘要 · Abstract (English)
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large Language Models (LLMs) for this task, but relies on simple interfaces that limit exploration of the full search space. We introduce RetroAgent, an LLM agent that bridges symbolic search and neural reasoning through a harness with structured memory. Through memory and chemistry tools, the agent observes the full search state, including explored routes, available alternatives, and properties of intermediates, enabling informed decisions grounded in both global progress and domain knowledge. Experiments on in-distribution and out-of-distribution benchmarks demonstrate that RetroAgent delivers strong performance and generalization.
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。