works on
episodic memory 1online planning 1safety validation 1training-free learning 1wet-lab automation 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.RO2026

LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents

Jingya Wang, Yuyang Gao, Liuzhenghao Lv +2

LabEvolver is a training‑free framework that gives wet‑lab robotic agents episodic memory and safety checks by combining an adaptive inner trial loop with an outer evolution loop t…