ReTRACE: Feedback-Guided LLM Agent in a Chemistry Harness for Retrosynthesis Planning
Abstract
ReTRACE, an LLM-based agent that integrates chemistry tools and evaluator feedback, generates retrosynthesis routes that pass audits and can be converted into executable wet-lab procedures.
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 \mbox{ReTRACE} (REtrosynthesis with Tool-orchestrated Reasoning And Context-aware Evidence), 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.
Get this paper in your agent:
hf papers read 2610.24744 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 1
jxtse/ReTRACE-train-data
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper