用智能体流程自动发现能保护胰岛素的聚合物，效率远超传统方法。
Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
- 用大模型+物理工具协同搜索，构建可迭代更新的虚拟实验环境。
- 找到相互作用能达-2263 kJ/mol的聚合物，比强化学习高68%。
- 适合做蛋白稳定化材料设计，可在普通电脑上运行。
冷链储存限制了数亿人获取胰岛素；开发一种热防护贴片聚合物或可解决此问题，但设计空间过大难以穷举实验。本文聚焦于此，提出一种智能体工作流：大语言模型（LLM）通过模型上下文协议（MCP）调用基于物理的工具，在有限预算内搜索离散的PSMILES空间，每次使用OpenMM Packmol矩阵评估。LLM作为隐式采集函数，依赖持续更新的“发现世界”——包括假设、文献结论与仿真结果。在匹配的基准预算下，最优自主实验达到-2263 kJ/mol的胰岛素-聚合物相互作用能，比强化学习基线提升68%，比贝叶斯优化高19%。三次独立实验均收敛至同一结构特征：重复单元中密集的氢键供体与受体。物理校验提前排除不可行构型与命名-结构不符项，避免误导后续步骤。整个科学阶段为CPU计算瓶颈，可在普通硬件上运行。该架构与工作流亦适用于其他蛋白质稳定任务，前提是存在可行的筛选代理。
原文摘要 · Abstract (English)
Cold-chain storage limits access to insulin for hundreds of millions of people; a thermally protective patch polymer could help, but the design space is too large for exhaustive experiment. Starting from that problem, we narrow to an agentic workflow: a large language model (LLM) calls physics-based tools through the Model Context Protocol (MCP), searching the discrete PSMILES space under a budget of OpenMM Packmol-matrix evaluations. The LLM acts as an implicit acquisition function conditioned on a persistent "discovery world": hypotheses, literature claims, and simulation outcomes updated each iteration. Under matched oracle budgets, the best autonomous campaign reaches an insulin-polymer interaction energy of -2263 kJ/mol, outperforming reinforcement-learning baselines by 68% and Bayesian optimization by 19%. Three independent campaigns converge on one structural motif (dense hydrogen-bond donors and acceptors per repeat unit) while physics checks reject infeasible packings and name-structure mismatches before they steer the next step. The science stage is CPU-bound and runs on commodity hardware. More broadly, the same architecture and workflow designed here applies to other protein-stabilization tasks whenever a tractable screening oracle is available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。