Self-Evolving Embodied Agents via Skill-Harness Evolution
Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, t...
Pei-Dong Wang, Zhiming Ma, Ying Chang et al.
· 7 citations
· ⚡1