论文研究 LLM 分子优化 Agent 的经验能否跨蛋白口袋复用
What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
这篇论文问了个挺实际的问题：药物设计 Agent 花对接算力学到的经验，能不能存下来给下一个蛋白口袋用。答案是能复用的部分主要是编辑动作本身，不是靶点信息。
论文基于 CrossDocked2020 测试集口袋，分析 LLM Agent 优化配体时留下的编辑-对接日志能否存入经验库供新口袋复用。以编辑位点的接触残基、动作和轮次作为 key，经验库能明显区分改善与恶化配体的编辑。研究发现可迁移的信号主要描述编辑动作和产出的分子本身，而不是靶点蛋白。作者据此提出，这类经验库更适合用来筛选 Agent 自己的对接候选方案，而不是直接指导该合成什么分子。
What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
LLM agents optimize a ligand in a protein pocket by editing it step by step and docking each edit. Recent agents first spend extra dockings probing the complex with controlled edits; guidance induced from these probes is reported to help more than the chemical knowledge the model already carries. The probes are then discarded with the instance that produced them, so the obvious next step is to keep them in an experience base, letting a new pocket inherit what earlier ones already paid for. Such a base is read through a \emph{key}: the record properties under which past edits are pooled and a new one is looked up. Using the full log of one such run over the CrossDocked2020 test-set pockets, we ask whether its keys recur on a pocket the base has never seen and still separate improving from worsening edits. \crchange{Using} the contacts at the site being edited, the action, and the round as \crchange{a} key, the base separates them sharply. Within our analysis, this separation is largely explained by how much the edit changed the molecule's size, the action, and the round, none of which describes the target. That is not because the target is irrelevant: naming it outright separates them several times more sharply. For a pocket absent from the base, transfer must rely on a description rather than its identity. Among the exact-match descriptions we evaluate, the more specific ones rarely recur, whereas the coarser ones provide little separation; the signals that do transfer primarily describe the edit and the molecule it produced rather than the target. Under the representations and lookup scheme studied here, an experience base may be more useful for prioritizing an agent's own proposals for docking than for directly prescribing what to build.
