自进化系统将生物实验流程自动转为可执行代码并持续优化。
A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols
- 构建多智能体系统，分层验证流程与代码生成
- 90.2%流程获专家偏好，89.5%通过设备合规检测
- 支持真实实验反馈闭环修正，适合自动化实验室研发
自主湿实验需要的不仅是合理的协议文本：生物意图、定量操作、设备约束和实验反馈必须在从协议设计到代码实现与物理执行的全链路中保持一致。我们开发了ProtoPilot，一个自进化多智能体系统，以及一个基于专家标准的基准与评估框架，用于测试这一转换过程作为实验自动化问题的可行性。该框架涵盖294个源自98个黄金标准协议的合成生物学与分子生物学任务，结合湿实验专家评分、设备级有效性校验及真实实验测试。ProtoPilot融合分层可验证性、多智能体协同与运行时更新技能库，实现协议生成、SOP扩展、SDK合规代码合成及基于湿实验反馈的流程修订。其在专家偏好排名中达Top@3 90.2%，协议到代码的通关率为89.5%，Opentrons设备通过率达88.24%，远超OpenTrons-AI的32.35%。湿实验验证获得可解释结果、Sanger测序确认产物，并通过反馈修正完成PCA组装的DNA目标，确立了可验证的自主实验路径。结果表明，该评估框架有效捕捉了自主湿实验自动化所需的关键要求，而ProtoPilot可通过流程与代码生成的验证执行及反馈驱动迭代来满足这些需求。
原文摘要 · Abstract (English)
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.
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。