Self-Evolving Embodied Agents via Skill-Harness Evolution
This work proposes SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts.
Pei-Dong Wang, Zhiming Ma, Ying Chang et al.
· 7 citations
· ⚡1