用智能体框架提升化学逆合成规划准确率，接近人类专家水平。
LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework
- 引入智能体评审机制，通过工具化推理动态评估约束条件。
- 在48个任务上达72.9%成功率，远超传统LLM基线。
- 适合需要高效、精准逆合成规划的药物研发人员。
大型语言模型（LLM）智能体评估器利用专用工具为LLM的决策提供依据，适用于科学发现，如受限逆合成规划。受限逆合成规划是化学中从市售起始原料到目标分子构建合成路径的关键但具挑战性的过程，需满足实际约束。本文提出LARC，首个基于LLM的智能体框架用于受约束的逆合成规划。LARC将智能体作为评审者（Agent-as-a-Judge）嵌入规划流程，通过基于工具的推理反馈引导并约束路线生成。我们在3类约束共48个精心设计的任务上严格评估了LARC，其成功率达72.9%，显著优于LLM基线，并在更短时间内接近人类专家水平。LARC具备可扩展性，是迈向人机协作化学家的重要一步。
原文摘要 · Abstract (English)
Large language model (LLM) agent evaluators leverage specialized tools to ground the rational decision-making of LLMs, making them well-suited to aid in scientific discoveries, such as constrained retrosynthesis planning. Constrained retrosynthesis planning is an essential, yet challenging, process within chemistry for identifying synthetic routes from commercially available starting materials to desired target molecules, subject to practical constraints. Here, we present LARC, the first LLM-based Agentic framework for Retrosynthesis planning under Constraints. LARC incorporates agentic constraint evaluation, through an Agent-as-a-Judge, directly into the retrosynthesis planning process, using agentic feedback grounded in tool-based reasoning to guide and constrain route generation. We rigorously evaluate LARC on a carefully curated set of 48 constrained retrosynthesis planning tasks across 3 constraint types. LARC achieves a 72.9% success rate on these tasks, vastly outperforming LLM baselines and approaching human expert-level success in substantially less time. The LARC framework is extensible, and serves as a first step towards an effective agentic tool or a co-scientist to human experts for constrained retrosynthesis.
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。