arXiv cs.CL· Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song, Lei Bai, Tianshu Yu·· 2 天前AI 评分22
LoopMol：用语义 LLM 代理实现闭环分子逆向设计
Closed-Loop Molecular Inverse Design with Semantic LLM Surrogates
AI 导读
LoopMol 是一个闭环分子逆向设计框架，用 LLM 代理直接基于任务指令、SMILES 优化历史和 oracle 反馈进行推理，每轮按探索-利用原则挑选参考分子并可附一句简短引导语。
正文 · 原文
Abstract:Practical molecular inverse design is rarely a one-shot generation problem; it often involves enriching a pool of molecules that match a desired property profile under a limited oracle budget. Bayesian optimization (BO) offers a natural framework for this setting, with standard Gaussian-process (GP) surrogates operating in continuous embedding spaces. We propose LoopMol, a closed-loop framework whose large language model (LLM) surrogate reasons directly over task instructions, SMILES-level optimization histories, and oracle feedback. At each iteration, the surrogate selects informative reference molecules under an exploration--exploitation principle, optionally with a concise guidance sentence. These outputs condition the next generation round and yield an inspectable optimization trace. Experiments on six drug and material tasks across three Llamole backbones show that the LLM-based variant improves over one-shot generation and is competitive with or stronger than GP-based BO. They also reveal a domain-dependent interface: reference-only conditioning performs better on binary drug tasks, while adding a concise guidance sentence generally benefits continuous material tasks.
| Comments: | 24 pages |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.22967 [cs.CL] |
| (or arXiv:2608.22967v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.22967 arXiv-issued DOI via DataCite |
Submission history
From: Yaoyao Xu [view email]
[v1]
Mon, 24 Aug 2026 08:30:01 UTC (1,112 KB)
[v2]
Fri, 11 Sep 2026 09:51:35 UTC (1,099 KB)
[v3]
Thu, 15 Oct 2026 11:09:21 UTC (1,158 KB)
来源：arXiv cs.CL · arxiv.org