ENPIRE: 现实世界中智能体机器人策略的自我改进
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
AI总结：
提出ENPIRE框架，通过环境重置、策略执行、结果验证和迭代优化的闭环反馈，使编码智能体自主改进机器人操作策略，在灵巧操作任务上达到99%成功率。
摘要：
在现实世界中实现灵巧的机器人操作严重依赖人工监督和算法工程，这成为追求通用物理智能的核心瓶颈。尽管新兴的编码智能体可以生成代码来自动化算法搜索，但其成功主要局限于数字环境。我们推测，自动化机器人研究缺失的抽象是一个可重复的反馈循环，用于现实世界策略改进：重置场景、执行策略、验证结果并优化下一次迭代。为弥补这一差距，我们引入ENPIRE，一个用于编码智能体的框架，通过四个核心模块实例化这一物理反馈例程：环境模块（EN）用于自动重置和验证，策略改进模块（PI）启动策略优化，推出模块（R）用于评估一个或多个并行运行的物理机器人的策略，以及进化模块（E），其中编码智能体分析日志、查阅文献、改进训练基础设施和算法代码以解决失败模式。这一闭环系统将现实世界操作学习转化为可控的优化过程，在最小化人工努力的同时，允许对训练方案和智能体变体进行公平消融。在ENPIRE的支持下，前沿编码智能体可以自主训练策略，在具有挑战性的灵巧操作任务（如整理针盒、紧固扎带和工具使用）上达到99%的成功率，并且当我们派遣智能体团队在机器人集群上工作时，这一过程会进一步加速。我们的结果展示了将编码智能体部署到物理世界中自主推进机器人技术的实用且可扩展的路径。
英文摘要：
Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable feedback loop for real-world policy improvement: reset the scene, execute a policy, verify the outcome, and refine the next iteration. To bridge this gap, we introduce ENPIRE, a harness framework for coding agents that instantiates this physical feedback routine with four core modules: an Environment module (EN) for automatic reset and verification, a Policy Improvement module (PI) that launches policy refinement, a Rollout module (R) to evaluate policies with one or multiple physical robots operating in parallel, and an Evolution module (E) in which coding agents analyze logs, consult literature, improve training infrastructure and algorithm code to address failure modes. This closed-loop system transforms real-world manipulation learning into a controllable optimization procedure, minimizing human effort while allowing fair ablations across training recipe and agent variants. Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks, such as organizing a pin box, fastening a zip tie, and tool use, a process that further accelerates when we dispatch an agent team on a robot fleet. Our results suggest a practical and scalable path toward deploying coding agents to autonomously advancing robotics in the physical world.
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。
