arXiv cs.AI· Yifei Wang, Botian Wang, YiFei Wang, Jiangtao Feng, Xinbo Zhang, Yawen Ouyang, Yixin Wu, Lihao Wang, Xiaoqing Zheng, Xuanjing Huang, Hao Zhou·· 2 小时前AI 评分41
Solvent：面向多步逆合成的长程推理 8B 大语言模型
Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis
AI 导读
研究者推出 Solvent，一个将长程推理扩展到多步逆合成任务的 8B 大语言模型。通过两轮后训练课程，它学会交替进行迭代合成规划、外部可得性验证和自适应路线修正；RL 带来 2.1 倍性能提升后，Solvent 在四个基准上取得 61.86% 的成绩，超越中等规模语言模型与既有搜索式逆合成系统，可比肩前沿万亿参数 LLM。
正文 · 原文
Authors:Yifei Wang, Botian Wang, YiFei Wang, Jiangtao Feng, Xinbo Zhang, Yawen Ouyang, Yixin Wu, Lihao Wang, Xiaoqing Zheng, Xuanjing Huang, Hao Zhou
Abstract:Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning to tackle the task. In its latest evolution, LLM reasoning has entered the long-horizon regime: models pursue objectives across interdependent steps, interact with environments, and adapt to feedback. This shift has markedly advanced LLM capabilities, as illustrated by breakthroughs in AI-driven mathematical research. At this frontier, we introduce Solvent, an 8B LLM that successfully extends long-horizon reasoning to multi-step retrosynthesis. Through a two-round post-training curriculum, Solvent learns to interleave iterative synthesis planning, external availability verification, and adaptive route revision. Experiments show that, following a $2.1\times$ performance boost from RL, Solvent scores 61.86% across four benchmarks, surpassing mid-scale language models and prior search-based retrosynthesis systems, and rivaling frontier trillion-parameter LLMs.
| Comments: | 49 pages, 18 figures. Code: this https URL ; Model: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32308 [cs.AI] |
| (or arXiv:2610.32308v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32308 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wang Yifei [view email]
[v1]
Fri, 23 Oct 2026 08:07:43 UTC (1,887 KB)
来源：arXiv cs.AI · arxiv.org