外观
论文arXiv 2609.276121 个月前
RegenHarness：一种带证据门控递归自我改进的机器人智能体框架
原文链接：RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement（arXiv 2609.27612 · 发布日期：2026-09-23）
RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement
RegenHarness通过证据门控执行架构连接任务规划与异构技能，并在真实四足仓库任务和独立回路中验证。
核心要点
- 长时程机器人执行需区分模型提议、控制器终止与经验证的任务完成。
- 系统以模型循环和智能体循环组织提议、派发、观察、验证、提交与有界恢复。
- 证据门控RSI依据执行记录提出配置改动，经回归检查和发布授权后接受。
- 真实部署展示仓库导航、全景巡检、视觉分析、消息递送、返回和语音报告。
验证范围与局限：验证范围包括一次真实四足机器人仓库部署，以及一个说明历史依赖完成判定的单独回路。
英文摘要 (Abstract)
Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We present RegenHarness, an evidence-gated robot-agent harness connecting task planning to heterogeneous robot skills. Its execution architecture couples a model loop for context-conditioned proposals with an agent loop for dispatch, observation, verification, commitment, and bounded recovery. Four role-isolated contexts separate planning, supervision, verification, and recovery inputs. Versioned memory distinguishes observed facts from accepted task progress, while an identity- and version-bound commit gate controls updates to trusted task state. The runtime combines duplicate-dispatch control, resource leases, and recovery budgets under explicit backend contracts, and checks the original user goal before reporting completion. To our knowledge, we are the first to introduce an evidence-gated recursive self-improvement (RSI) protocol for embodied robotic agents. Across missions, execution records motivate candidate changes to context rules, task templates, routing, and recovery policies; fixed regression checks and release authorization govern their acceptance; versioned rollout and rollback preserve configuration traceability. This RSI protocol revises the harness configuration without online model-weight updates or permission to weaken the commit gate. A real quadruped deployment documents voice-triggered warehouse navigation, panoramic inspection, visual analysis, message delivery, return, and spoken reporting through linked audio, images, trajectories, and receipts. A separate circuit demonstrates why completion depends on execution history rather than endpoint proximity alone. Together, the cases demonstrate integrated perception, physical execution, communication, and history-dependent completion in real-world robot tasks.
作者：Kailin Wang, Haoxiang Jie, Yan Yaoyuan, Zhiyou Heng, Zhaosong Li
来源
本页事实对应的公开页面，以原文为准。