发表机构
University of Manchester; Stanford University; NIHR Manchester Biomedical Research Centre（曼彻斯特大学; 斯坦福大学; NIHR曼彻斯特生物医学研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一个本地可部署的紧凑语言模型框架，通过规划18个工具调用支持早期药物发现，经LoRA微调后实现高精度规划，但组合泛化仍是挑战。
AI 中文摘要
早期计算药物发现需要在多步骤工作流中协调异构的科学工具。我们提出一个轻量级的、工具增强的框架，其中本地可部署的紧凑语言模型规划对18个模块化工具的调用。一个统一分子模式（Unified Molecular Schema）维护共享的分子记录，而插件接口支持工具替换和扩展。我们通过工作流图路径覆盖构建了1,263个手工精炼的查询-规划对，并对三个紧凑模型系列应用LoRA微调。在查询级划分下，所有微调模型在47个保留的跨组查询上生成完全可解析且符合模式的规划。Llama 3.2-3B实现了工具选择F1为0.998，序列精确匹配为0.979，参数F1为0.960。在更严格的工作流分组划分下，该划分排除了跨分区的相同有序工具序列，序列精确匹配达到0.452至0.548，突出了紧凑模型在生成训练中未见过的完整工作流路径方面的剩余困难。这些结果证明了紧凑、本地可部署规划的可行性，同时将组合泛化确定为进一步改进的重要方向。
英文摘要
Early-stage computational drug discovery requires coordinating heterogeneous scientific tools across multi-step workflows. We present a lightweight, tool-augmented framework in which a locally deployable compact language model plans calls to 18 modular tools. A Unified Molecular Schema maintains shared molecular records, while a plug-in interface supports tool replacement and extension. We construct 1,263 manually refined query-plan pairs through workflow-graph path coverage and apply LoRA fine-tuning to three compact model families. Under the query-level split, all fine-tuned models generate fully parseable and schema-compliant plans on 47 held-out cross-group queries. Llama 3.2-3B achieves a tool-selection F1 of 0.998, sequence exact match of 0.979, and argument F1 of 0.960. Under the stricter workflow-grouped split, which excludes identical ordered tool sequences across partitions, sequence exact match reaches 0.452 to 0.548, highlighting the remaining difficulty for compact models in generating complete workflow paths unseen during training. These results demonstrate the feasibility of compact, locally deployable planning while identifying compositional generalization as an important direction for further improvement.
Comments22 pages, 4 figures. Accepted at the AI for Drug Discovery Workshop, NeurIPS 2026
