用智能体架构自动优化机器人策略，失败工具可追踪、可恢复。
You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvement
- LLM 控制器驱动临时工作者，通过训练-评估-改进循环迭代优化
- 错误提升率降至0.001（原0.005–0.021），支持随时中断与恢复
- 适合需要高可靠性、可追溯的机器人策略开发团队
类代码智能体（如Claude Code、Codex）构建了软件开发闭环：主智能体管理流程，子智能体分析执行，工具完成具体工作。本文将该架构迁移至机器人策略优化，核心差异在于：机器人工具（训练策略、训练流水线、数据采集）常失效，因此必须在每次调用时测量并记录其质量，并在背后产物变更时自动过期。AgenticRobotics 是一个后端无关的控制平面，由大模型控制器驱动可丢弃的工作节点，完成持久化的“训练-评估-改进”事务：包含不可变目标、控制器拥有的度量、基于提交密钥的崩溃恢复、证据分级的技能库，以及标准化调用接口的工具注册表。标题是操作性主张，非选择性主张：操作者可离开，因晋升受证据约束、状态可恢复、能力质量来自记录——并非因为循环比人选更优；在一条测试链上，它并未表现更好。这些机制显著提升了错误晋升控制（0.001/运行，相比0.005–0.021发布版），支持任意时间点有效决策（可选中断），在注入杀死信号下零丢失或重复影响，且六类工具篡改均被签名验证器捕获。
原文摘要 · Abstract (English)
Coding agents such as Claude Code and Codex close the software loop: a main agent manages the loop, subagents analyze and execute, tools do the work. We port this architecture to robot-policy improvement, where one difference dominates the design: robotic tools---trained policies, training pipelines, data collection---fail routinely, so a tool's quality must be measured, recorded at every call, and expired when the artifact behind it changes. AgenticRobotics is a backend-independent control plane in which an LLM controller drives disposable workers through durable train--evaluate--improve transactions: an immutable objective, controller-owned measurement, commit-keyed crash recovery, an evidence-graded skill library, and a tool registry with a standardized, recorded call surface. The title is an operational claim, not a selection claim: the operator can leave because promotion is evidence-gated, state is recoverable, and capability quality is derived from records---not because the loop picks better checkpoints than a human; on the one lineage we measured, it does not. The gates measurably buy false-promotion control (0.001 per run hardened versus 0.005--0.021 shipped), anytime-valid decisions under optional stopping, zero lost or duplicate effects under kill injection, and six of six artifact-tampering classes caught by a signed verifier.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。