EmbodiedEvo：面向物理智能的自改进编码智能体
EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence
AI总结：
EmbodiedEvo是面向物理智能的自改进编码智能体，通过在Playground场景演化技能与经验教训，在RoboDojo-Sim上表现优于官方结果，还能跨模型传递经验降低执行成本。
摘要：
将通用智能体引入物理世界需要物理智能的可执行表示。与直接将观测结果和语言指令映射到动作的视觉-语言-动作（VLA）模型相比，代码能让控制逻辑更明确且可复用，不仅可作为策略表示，还可作为智能体解决任务的工作空间。智能体无需遵循规划、执行、验证的规定流程，可自主检查状态、修改并执行代码，利用反馈选择下一步。SWE式循环在数字环境中的成功促使其扩展到物理任务，但物理执行仍易出现反复失败。为保留并优化后续场景的经验，我们提出EmbodiedEvo：编码智能体通过对单个Playground场景的反馈演化出可复用的技能与经验教训，随后将生成的工具链固化以适配多样新场景。在RoboDojo-Sim上，EmbodiedEvo的平均得分为44.48，成功率为37.82%，超过所有官方验证结果。配对测试显示，其在依赖记忆的任务上增益最大，且能成功复用协调程序，但精细接触控制仍存在困难。更强模型的经验也能提升较弱执行器：Astra的经验使Sol和Luna的成功率较无经验时分别提升8.86和5.50个百分点。与原始交互历史相比，技能与经验教训在任务表现相当的情况下，执行成本降低53.0%。
英文摘要：
Bringing general-purpose agents into the physical world calls for an executable representation of physical intelligence. Compared with vision-language-action (VLA) models, which map observations and language instructions directly to actions, code makes control logic explicit and reusable. Code can serve not only as a policy representation but also as the workspace in which the agent solves a task. Rather than following a prescribed workflow of planning, execution, and verification, the agent can autonomously inspect the state, revise and execute code, and use feedback to choose the next step. The success of this SWE-style loop in digital environments motivates its extension to physical tasks. Yet physical execution remains prone to recurring failures. To retain and refine experience for later scenes, we introduce EmbodiedEvo, where a coding agent evolves reusable Skills and Lessons through feedback on a single Playground scene, then freezes the resulting harness for diverse new scenes. On RoboDojo-Sim, EmbodiedEvo achieves an average score of 44.48 and a success rate of 37.82\%, surpassing all officially verified results. Paired tests show the largest gains on memory-dependent tasks and successful reuse of coordinated procedures, while fine contact control remains difficult. Experience from stronger models also improves weaker executors: Astra's experience raises Sol and Luna's success rates by 8.86 and 5.50 percentage points over no experience. Compared with raw interaction history, Skills and Lessons achieve comparable task performance at 53.0\% lower execution cost.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
