跳到正文
arXiv cs.AI· Hongxuan Shi, Hankz Hankui Zhuo·· 3 小时前AI 评分38

Verification-Guided Reflow(VGR):用反应验证反馈与证据时机改进逆合成规划

Verification-Guided Retrosynthesis: Reaction Feedback and Evidence Timing

AI 导读

一项 arXiv cs.AI 研究提出 Verification-Guided Reflow(VGR),将反应验证作为 AND/OR 搜索中的决策动作,用于逆合成路线规划。

正文 · 原文

View PDF HTML (experimental)

Abstract:Retrosynthesis planning seeks synthesis routes from purchasable starting materials to a target molecule. Search over predicted reactions can connect a target to available materials, yet an infeasible reaction can invalidate the resulting route. Evaluating route quality only after search has finished cannot correct errors made during search. We introduce Verification-Guided Reflow (VGR), incorporating reaction verification as a decision action in AND/OR search. Verification results are represented as binary verdicts; queries are scheduled from the search structure, and acquired verdicts exclude reactions or adjust search priorities. We define verified solvability as the fraction of targets for which a complete route accepted stepwise by the verifier is found. On Retro190, feeding verification results into search increases verified solvability from 51.1% to 62.6% relative to route evaluation without feedback. Further controlled experiments show that earlier verification and immediate prioritization of accepted reactions each improve route discovery, yet combining them performs worse than either change alone. We therefore propose early pruning and delayed guidance: rejected reactions are pruned immediately, while accepted reactions gain search priority when processed as part of a complete candidate route. In a separate comparison with the verification scheduling rule fixed, this strategy increases verified solvability from 61.1% with immediate guidance to 71.1%, using fewer proposal calls and unique verifier queries.
Comments: 12 pages, including appendices
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2610.38245 [cs.AI]
  (or arXiv:2610.38245v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2610.38245

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hongxuan Shi [view email]
[v1] Wed, 28 Oct 2026 03:50:35 UTC (24 KB)

来源:arXiv cs.AI · arxiv.org