无需训练，让实验机器人通过经验自动优化操作，更安全高效。
LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents
- 用内外双循环机制，从真实实验中提炼可复用的经验技能。
- 实测减少48.2%的调节时间、60.0%的安全拦截次数。
- 适合自动化实验、科学发现等需要安全试错的场景。
我们提出LabEvolver，一个无需训练的框架，使安全且具情境感知的湿实验代理能够从执行经验中获取情景记忆。LabEvolver结合了基于状态的内部试错循环（用于自适应感知、在线规划与安全验证）和外部进化循环（将完成的轨迹提炼为可复用的技能、策略与安全经验）。在机器人溶液制备任务中，该框架展示了实际可行性，使pH调节完成时间减少48.2%，安全门拦截次数降低60.0%。在ALFWorld上，其累积成功率在20步内从使用ReAct时的76.2%提升至91.4%，覆盖500个连续任务，证明了其超越湿实验场景的通用性。这些结果支持‘边做边学’的经验进化是实现闭环自动化科学发现的可行路径。项目页面见：https://andygao6186.github.io/LabEvolver/
原文摘要 · Abstract (English)
We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience. LabEvolver couples a state-grounded inner trial loop for adaptive perception, online planning, and safety validation with an outer evolution loop that distills completed trajectories into reusable skill, strategy, and safety experience. On robotic solution-preparation tasks, LabEvolver demonstrates real-world feasibility, reducing pH-regulation completion time and safety-gate intercepts by 48.2% and 60.0%, respectively. On ALFWorld, it further improves cumulative success rate within 20 steps from 76.2% with ReAct to 91.4% over 500 continual tasks, showing generality beyond wet-lab settings. These results support learn-by-doing experience evolution as a feasible path toward closed-loop automated scientific discovery. The project page is available at https://andygao6186.github.io/LabEvolver/.
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。