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, showing generality beyond wet-lab settings.
Abstract
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/.
RACaP is introduced, an agentic framework that moves coding to evolution and uses a Reasoning-and-Acting loop to call frozen, typed Policy APIs at deployment and shows that separating reusable code from runtime decisions supports continued evolution, effective transfer, and efficient long-horizon control.
Ze-Xi Li, Ye-Hang Zhang, Hao-Jian Huang et al.· 1 citation
Transferring robotic skills from simulation to reality requires task knowledge that remains usable across differences in perception, dynamics, and embodiment. We introduce Skill2Real, an agentic policy framework that learns executable skills through a shared application programming interface (API). A Proposer-Verifier-...
Xin-Chen He, Si-Yu Ma, Chang Yu et al.· 1 citation
Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce ManiGuard, a specification-grounded framework for evaluating and improving the safety of foundation-model manipulation, comprising the ManiGuard...
Yi Peng, Philip Wang, Simon Sinong Zhan et al.· 2 citations· ⚡1
We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attempts, and retaining what it learns, without retraining. Our key insight is that a broad controller already holds much of the competence a new...
Zhuo Lin, Sirui Xu, Liu-Yu Bian et al.· 0 citations
FIND is introduced, an agentic real-world RL framework that closes the loop between scene understanding, weakness-aware practice, self-evaluation, and policy improvement in a persistent workspace and reframes autonomous practice as a scene-conditioned, performance-aware task-selection problem.
Yuan Fang, Ze-Chu Li, Hao-Lei Tong et al.· 2 citations
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model wei...
Yen-Jen Wang, Hao-Zhe Jiang, Shu-Ying Deng et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
