arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.30587cs.ROcs.DC
收藏

知晓何时升级:面向云-本地具身智能体的评论者引导式自适应执行

Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Cornell University(康奈尔大学);Cisco(思科公司)

Wei Zhang, Lirong Xiang, Charles Fleming

AI总结:

该研究提出CARE框架,通过评论者引导动态在本地与云端模型间升级控制权,在具身基准中提升任务成功率并降低动作间延迟。

摘要:

基础模型智能体的最新进展已催生了越来越强大的具身系统,可用于长程规划与交互。然而,具身智能体在持续感知变化环境并执行动作时,需要快速的闭环决策。部署强大的云端智能体会导致平台在连续动作之间闲置数秒,而轻量级本地模型响应迅速但更易出错。现有分层架构通常为模型分配固定角色,而传统模型路由器则针对每个请求做出无状态决策。我们提出CARE,一种评论者引导式自适应执行框架,可动态决定何时将控制权从本地执行器升级至更强的云端模型。轻量级评论者模型监控执行可靠性,当本地执行变得不可靠时触发升级;升级后,控制权将持续保留,直至智能体恢复,避免逐步骤切换。为支持此类控制权转移,共享交接内存在各执行器间维护执行上下文与任务级进度,使模型无需从头重启即可介入。在各类具身基准测试中,CARE相较于评估的最强协作基线,任务成功率提升了6.3至18.3个百分点;CARE还接近或超过仅云端方案的成功率,同时将动作间的中位延迟降低了28.8至82.6%。

英文摘要:

Recent advances in foundation-model agents have enabled increasingly capable embodied systems for long-horizon planning and interaction. However, embodied agents require fast, closed-loop decisions as they continuously perceive and act on a changing environment. Deploying strong cloud agents leaves the platform idle for seconds between consecutive actions, while lightweight local models respond quickly but are more vulnerable to errors. Existing hierarchical architectures typically assign models fixed roles, whereas conventional model routers make stateless per-request decisions. We present CARE, a critic-guided adaptive execution framework that dynamically determines when to escalate control from a local executor to a stronger cloud model. A lightweight critic model monitors execution reliability and triggers escalation when local execution becomes unreliable; once escalated, control persists until the agent recovers, avoiding step-wise switching. To support such control transfer, a shared handoff memory maintains execution context and task-level progress across executors, enabling the model to intervene without restarting from scratch. Across diverse embodied benchmarks, CARE improves task success by 6.3-18.3 percentage points over the strongest evaluated collaboration baseline. CARE further approaches or exceeds Cloud-only success while reducing median time-between-action latency by 28.8-82.6%.

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。

↑