动作-观察-重写：多模态编码代理作为机器人操作的上下文政策学习者
Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation
AI总结：
AOR框架通过生成可执行代码使机器人操作策略学习无需演示或奖励工程。
摘要：
能否通过推理自身失败来让多模态语言模型学习操纵物理对象，而无需梯度更新、演示或奖励工程？我们认为答案是肯定的，在我们精确刻画的条件下。我们提出了Act-Observe-Rewrite（AOR）框架，其中LLM代理通过在试验之间合成完全新的可执行Python控制器代码来改进机器人操作策略，受视觉观察和结构化事件结果的引导。与以往将LLM固定在预定义技能库或使用代码生成进行单次计划合成的工作不同，AOR使完整的低层运动控制实现成为LLM推理的单位，使代理能够改变不仅机器人做什么，而是如何做。核心主张是可解释的代码作为策略表示，创建了与不透明神经策略不同的上下文学习：代理可以诊断系统性失败并重写其原因。我们验证了这一点，跨三个Robosuite操作任务报告了有希望的结果，代理在没有演示、奖励工程或梯度更新的情况下实现了高成功率。
英文摘要：
Can a multimodal language model learn to manipulate physical objects by reasoning about its own failures-without gradient updates, demonstrations, or reward engineering? We argue the answer is yes, under conditions we characterise precisely. We present Act-Observe-Rewrite (AOR), a framework in which an LLM agent improves a robot manipulation policy by synthesising entirely new executable Python controller code between trials, guided by visual observations and structured episode outcomes. Unlike prior work that grounds LLMs in pre-defined skill libraries or uses code generation for one-shot plan synthesis, AOR makes the full low-level motor control implementation the unit of LLM reasoning, enabling the agent to change not just what the robot does, but how it does it. The central claim is that interpretable code as the policy representation creates a qualitatively different kind of in-context learning from opaque neural policies: the agent can diagnose systematic failures and rewrite their causes. We validate this across three robosuite manipulation tasks and report promising results, with the agent achieving high success rates without demonstrations, reward engineering, or gradient updates.
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。
