EMHO: EMbodied Agent Harness Optimization via Experience Traces
- 类型：arxiv
- 标识：2610.08432
- 链接：http://arxiv.org/abs/2610.08432v1
- 主分类：evaluation
- 形态：method
- TLDR：Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning, context, and tool use is typically engineered. We ask whether this harness can instead improve itself directly from experience traces under sparse environmental feedback. We propose EMbodied Agent Harness Optimization (EMHO), a self-evolving framework that keeps the embodied model frozen and iteratively revises its harness by analyzing execution trajectories and prior harness history. EMHO optimizes beyond skills or recovery prompts, modifying
- 副分类：agent
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-10-07-agent-rag-longcontext-candidates.json