Self-Evolving Embodied Agents via Skill-Harness Evolution

Excerpt

arXiv:2608.11350v2 Announce Type: replace Abstract: 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, they require additional data, rewards, and training runs; meanwhile, many train-free code-centric approaches rely on programmable