一种用于自动生成和执行生物实验协议的自演化智能体系统
A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols
AI总结：
提出自演化多智能体系统ProtoPilot，结合专家基准与评估框架，将生物协议自动转化为可执行代码，并通过湿实验反馈迭代优化，实现高通过率的自主实验。
摘要：
自主湿实验不仅需要合理的协议文本：生物意图、定量程序、设备约束和实验反馈必须从协议和SOP设计到代码和物理执行保持一致。我们开发了ProtoPilot，一个自演化的多智能体系统，以及一个基于专家知识的基准和评估框架，用于测试这种转换作为实验自动化问题。该框架涵盖294个合成生物学和分子生物学任务，源自98个金标准协议、湿实验专家评分标准、设备级有效性门控和实际实验测试。ProtoPilot结合了分层可验证性、多智能体编排和运行时更新的技能库，以生成协议、扩展SOP、合成符合SDK的代码并根据湿实验反馈修订工作流程。它实现了90.2%的Top@3专家偏好率、89.5%的整体协议到代码门控通过率和88.24%的Opentrons通过率，而OpenTrons-AI为32.35%。湿实验验证产生了可解释的读数、Sanger确认的产物和反馈校正的PCA组装DNA靶标，为自主实验建立了可验证的路径。这些结果表明，评估框架捕获了自主湿实验自动化的执行相关要求，并且ProtoPilot通过将协议和代码生成转化为经过验证的执行和反馈引导的修订来满足这些要求。
英文摘要：
Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conversion as an experimental automation problem. The framework spans 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols, wet-lab expert rubrics, device-level validity gates and real experimental tests. ProtoPilot incorporates layer-wise verifiability, multi-agent orchestration and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code and revise workflows from wet-lab feedback. It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5% and an Opentrons pass rate of 88.24%, compared with 32.35% for OpenTrons-AI. Wet-lab validation produced interpretable readouts, Sanger-confirmed products and feedback-corrected PCA-assembled DNA targets, establishing a verifiable route to autonomous experimentation. Together, these results show that the evaluation framework captures execution-relevant requirements for autonomous wet-lab automation, and that ProtoPilot can meet them by converting protocol and code generation into validated execution and feedback-guided revision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
