Rachel: A general-purpose language model directs and revises retrosynthetic routes

📅 2026-09-20
📈 Citations: 0
✨ Influential: 0
📄 PDF
🤖 AI Summary
研究解决了逆合成路线规划问题,通过开发名为Rachel的环境,利用通用大型语言模型GPT-5.5直接指导和修正化学合成路径。
📝 Abstract
Retrosynthetic planning advances through decisions that reshape the remaining chemical problem: a locally plausible disconnection can leave precursors whose chemoselectivity constraints complicate the rest of the route. Existing planners often channel model proposals through search or template procedures, leaving open whether a general-purpose large language model (LLM) can itself sustain and revise route strategy. We developed Rachel, a stateful environment that executes and checks LLM-directed chemistry but prescribes neither a search policy nor a stopping rule. Without supplied reference routes or route-level solutions, GPT-5.5 achieved strict closure for 111 of 120 PaRoutes120 targets and 24 of 25 targets in the separate RF25 difficult-target cohort. RF25 was drawn largely from studies published after GPT-5.5's reported knowledge cutoff. Closure required complete routes and independent source resolution of every terminal precursor after planning. On a shared PaRoutes subset, forward-model support exceeded that of most comparator methods, and Rachel received the highest mean overall route score from both method-blinded LLM evaluators. Recorded trajectories showed continued model-proposed chemistry, with revised strategies carried into subsequent steps. Replacing LLM route decisions with fixed policies reduced strict closure to 6-15/120 despite continued local chemical execution; restricting planning support also reduced closure in RF25. Within Rachel, a general-purpose LLM coordinated successive chemical choices and revised its strategy as earlier decisions reshaped the remaining problems.
Problem

Research questions and friction points this paper is trying to address.

retrosynthetic planning
large language model
route strategy
chemical problem
chemoselectivity constraints
Innovation

Methods, ideas, or system contributions that make the work stand out.

general-purpose large language model
retrosynthetic planning
stateful environment
autonomous strategy revision
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Qisheng Li
Qisheng Li
Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, China
S
Shunchao Jiang
Zhenzhida Biotechnology (Shanghai) Co., Ltd.
C
Chen Qi
Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, China
X
Xin Su
State Key Laboratory of Organic–Inorganic Composites, Beijing Advanced Innovation Center for Soft Matter Science and Engineering, College of Life Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
Da Han
Da Han
Professor, Shanghai Jiao Tong University, Hangzhou Institute of Medicine (HIM), CAS
DNA nanotechnologyBiosensorsNanofabrications
G
Guangyong Chen
Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, China