[论文] AgentRoboCritic: Understanding the Capability of Frontier Agents on Di...
研究领域: NLP 作者: Yiyang Du, Yuxuan Kuang, Qitao Zhao, Yixuan Wang, Zhanqiu Guo, Yi Xu, Xin Li, Wenbin He, Liu Ren, Chenyan Xiong 发布时间: 2026-11-19 arXiv: 2611.26613
论文概要
研究领域: NLP 作者: Yiyang Du, Yuxuan Kuang, Qitao Zhao, Yixuan Wang, Zhanqiu Guo, Yi Xu, Xin Li, Wenbin He, Liu Ren, Chenyan Xiong 发布时间: 2026-11-19 arXiv: 2611.26613
中文摘要
GPT-6 Astra等前沿多模态语言智能体已展示出不依赖高层原语、直接通过低层数值动作控制机器人的强大能力。然而,现有基准仅报告回合级成功率,既不展示这些智能体如何成功,也不揭示它们在何处失败。本文对前沿智能体在直接机器人控制上的能力进行系统性的动作级分析,横跨12个操作基准。我们提出AgentRoboCritic,一个意图驱动的批评框架:策略智能体在输出每个动作的同时声明局部意图,批评智能体对照该意图评估动作结果和失败模式。动作级分析展示了前沿智能体在直接机器人控制上的潜力:从局部执行失败中闭环恢复、跨多样场景的可靠语义落地、以及无需任务特定适应的强零样本操作能力。同时也识别出当前局限:与任务相关的物理执行瓶颈(如抓取和对齐),以及跨失败模式不均衡的恢复能力。我们在400动作的人工标注基准上验证批评器,并发布12,844条标注动作数据集及微调开源批评器Muse-Glimmer-30B,其失败模式分类准确率从32.58%提升至74.24%,实现低成本动作级分析。
原文摘要
Frontier multimodal language agents such as GPT-6 Astra have demonstrated strong capabilities in controlling robots directly via low-level numerical actions without high-level primitives. However, existing benchmarks report only episode-level success rates, which show neither how these agents succeed nor where they fail. In this paper, we present a systematic action-level analysis of frontier agents on direct robot control across 12 manipulation benchmarks. We introduce AgentRoboCritic, an intent-grounded critique framework in which the policy agent states a local intent alongside each action, and a critic evaluates the action's outcome and failure mode against this intent. Our action-level analysis demonstrates the promising capabilities of frontier agents on direct robot control, includi...
*自动采集于 2026-11-21*
#论文 #arXiv #NLP #小凯