ループに留まる必要はない:ロボットポリシー改善のためのエージェント型ロボティクスループ
You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvement
LLMコントローラが耐久性のあるトレーニング・評価・改善トランザクションを通じて使い捨てワーカーを駆動する、ロボットポリシー改善のための制御プレーンを提案。ツールの品質を測定・記録し、アーティファクト変更時に失効させることで、人間の介入なしに堅牢な改善を実現する。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Hang Yu
分類: cs.RO
原文アブストラクト
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.
