发表机构
Korea University; University of Arkansas; University of Wisconsin–Madison（高丽大学; 阿肯色大学; 威斯康星大学麦迪逊分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EMHO通过经验轨迹自我优化具身智能体的控制框架，在保持模型冻结的同时提升导航和操作任务成功率，并重塑智能体与环境交互方式。
AI 中文摘要
改进具身智能体通常侧重于通过训练优化底层模型，而控制规划、上下文和工具使用的周边智能体框架通常是人工设计的。我们探讨该框架能否在稀疏环境反馈下，直接从经验轨迹中自我改进。我们提出具身智能体框架优化（EMHO），这是一个自我进化的框架，保持具身模型冻结，通过分析执行轨迹和先前的框架历史来迭代修订其框架。EMHO的优化超越了技能或恢复提示，它修改了智能体监控进度、使用视觉工具、基于观察进行推理以及应对失败的方式。为支持单一框架处理多个子任务，我们引入了EMHO-Merge，通过使用回合级收益和损失来指导基于证据的修订，解决跨子任务联合优化单一共享框架时的权衡问题，明确何时以及如何应用修订后的行为。我们在EmbodiedBench上对EMHO进行了导航和操作任务的评估，EMHO持续提升了Qwen 9B和27B模型的任务成功率。定性分析表明，EMHO不仅限于从失败和低效行动中恢复，还重塑了具身智能体解释和与环境交互的方式。
英文摘要
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 how the agent monitors progress, uses vision tools, grounds observations, and responds to failures. To support multiple subtasks with a single harness, we introduce EMHO-Merge, which addresses trade-offs in jointly optimizing a single shared harness across subtasks by using episode-level gains and losses to guide evidence-supported refinement of when and how revised behaviors are applied. We evaluate EMHO on EmbodiedBench across navigation and manipulation tasks, and EMHO consistently improves task success for both Qwen 9B and 27B models. Qualitative analysis shows that EMHO goes beyond recovering from failures and unproductive actions to reshape how the embodied agent interprets and interacts with its environment.
