任务(项目管理)
回顾性分析
计算机科学
树(集合论)
人工智能
空格(标点符号)
领域(数学分析)
数据科学
结构化预测
序列(生物学)
机器学习
简单(哲学)
过程(计算)
工程类
方案(数学)
点(几何)
管理科学
领域(数学)
人机交互
搜索算法
极限(数学)
专家系统
知识管理
工作(物理)
人工神经网络
选择(遗传算法)
决策树
作者
Yanqiao Zhu,Jingru Gan,Xiaoqi Sun,Fang Sun,Y Shi,Md Tauhidul Islam,Chao Shang,Wenhao Gao,Connor W. Coley,Yizhou Sun,Wei Wang
标识
DOI:10.48550/arxiv.2607.14512
摘要
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large Language Models (LLMs) for this task, but relies on simple interfaces that limit exploration of the full search space. We introduce RetroAgent, an LLM agent that bridges symbolic search and neural reasoning through a harness with structured memory. Through memory and chemistry tools, the agent observes the full search state, including explored routes, available alternatives, and properties of intermediates, enabling informed decisions grounded in both global progress and domain knowledge. Experiments on in-distribution and out-of-distribution benchmarks demonstrate that RetroAgent delivers strong performance and generalization.
科研通智能强力驱动
Strongly Powered by AbleSci AI