ReTRACE：用 LLM 智能体做逆合成路线规划
ReTRACE: Feedback-Guided LLM Agent in a Chemistry Harness for Retrosynthesis Planning
一篇把 Claude Opus 4.8 变成合成化学助手的论文，逆合成路线三成基准过审率超 87%，还做了湿实验验证。
arXiv 论文 ReTRACE 将 LLM 放入化学工具环境中做逆合成规划，整合分子工具、单步预测引擎、可购买原料库与路线记忆。路线由新指标评估，结合程序化检查与对抗式 LLM 审查，并由合成化学家校验。基于 Claude Opus 4.8 的智能体在搜索中持续根据评估反馈回溯修正路线，在三个基准上 top 10 路线通过审计的比例分别为 87.4%、95.0%、86.7%。两次前瞻性湿实验验证路线经专家修改后可执行。
ReTRACE: Feedback-Guided LLM Agent in a Chemistry Harness for Retrosynthesis Planning
Computer-aided retrosynthesis has advanced through single-step prediction, tree search and route scoring, but complex targets still require judgement over the whole route, where stereochemistry, functional-group compatibility, cost and greenness interact. Here we present \textbf{\mbox{ReTRACE}} (\textbf{RE}trosynthesis with \textbf{T}ool-orchestrated \textbf{R}easoning \textbf{A}nd \textbf{C}ontext-aware \textbf{E}vidence), an agent that places a large language model (LLM) in a chemistry harness that integrates molecular tools, complementary single-step prediction engines, a purchasable starting-material library, a route memory and a multi-criterion route evaluator. Routes are judged by a new metric that combines programmatic checks with adversarial LLM review, and its verdicts are compared with a synthetic chemist's. The agent learns continually from evaluator feedback during search, diagnosing weak routes and backtracking to revise them. With Claude Opus 4.8, at least one of the top 10 routes proposed by ReTRACE passed the audit for 87.4\%, 95.0\% and 86.7\% of targets on the three benchmarks. Two prospective wet-lab syntheses show that ReTRACE route proposals can be converted into executable procedures after expert revision.
