arXiv cs.AI· Lingjun Mao, Jinglin Cao, Lukun He, Wenpeng Xu, Yuchen Yan, Hengyu Jin, Zijun Zhang, Jinzhou Tang, Songyao Jin, Ziche Liu, Yifei Shao, Junbo Huang, Fang Nan, Ruobing Han, Ziqiao Xi, Ziming Xu, Shuang Liang, Sibo Zhu, Wenyi Wu, Xinyue Wang, Yiming Huang, Xinkai Zou, Gao Zhu, Kun Zhou, Biwei Huang·· 3 小时前AI 评分47
RobotAgentBench 发布：面向开放世界机器人自主性的评测基准
RobotAgentBench: Towards Open-world Robot Autonomy
AI 导读
研究团队推出机器人智能体评测基准 RobotAgentBench（RAB），在真实开放世界家庭环境中评估机器人自主能力。该基准通过人机协同的真实到仿真流程构建 50 种家庭布局，涵盖 90 个原子任务、18 个短程任务、8 个长程任务和 4 个开放式场景，从任务发现、上下文推理、操作、失败恢复和鲁棒性五个维度及场景层面进行评测。
正文 · 原文
Authors:Lingjun Mao, Jinglin Cao, Lukun He, Wenpeng Xu, Yuchen Yan, Hengyu Jin, Zijun Zhang, Jinzhou Tang, Songyao Jin, Ziche Liu, Yifei Shao, Junbo Huang, Fang Nan, Ruobing Han, Ziqiao Xi, Ziming Xu, Shuang Liang, Sibo Zhu, Wenyi Wu, Xinyue Wang, Yiming Huang, Xinkai Zou, Gao Zhu, Kun Zhou, Biwei Huang
Abstract:Recent advances in vision-language-action (VLA) and world-action models (WAMs) have significantly improved robotic manipulation, yet deploying robots in the open world demands a higher level of autonomy beyond executing predefined tasks. Robot agents offer a promising paradigm for this transition, integrating task discovery, contextual reasoning, physical execution, and adaptive recovery into a closed interaction loop. However, existing benchmarks largely evaluate isolated capabilities, failing to capture the complexity of open-world robot autonomy. We introduce RobotAgentBench (RAB), a comprehensive benchmark for evaluating robot agents in realistic, open-world household environments. Through an agent-assisted, human-in-the-loop real-to-sim pipeline, RAB constructs 50 diverse household layouts with interactive objects and physically grounded tasks, encompassing 90 atomic tasks, 18 short-horizon tasks, 8 long-horizon tasks, and 4 open-ended scenarios. RAB provides a multi-level evaluation of robot agent capabilities: (1) task-level assessments systematically examine five complementary dimensions: task discovery, context reasoning, manipulation, failure recovery, and robustness; (2) scenario-level evaluation assesses how agents integrate these capabilities to autonomously fulfill high-level user needs. Furthermore, RAB enables systematic comparisons of standalone VLA/WAM models and diverse robot agent architectures under a unified planning-execution-verification framework. Extensive experiments reveal substantial gaps between manipulation and autonomy, demonstrate the advantages of agentic architectures and recursive self-improvement, and highlight the remaining challenges toward open-world robot autonomy.
| Comments: | Project page: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34649 [cs.RO] |
| (or arXiv:2610.34649v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34649 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lingjun Mao [view email]
[v1]
Mon, 26 Oct 2026 00:26:30 UTC (20,092 KB)
来源：arXiv cs.AI · arxiv.org