arXiv 2604.168862026-04-18cs.RO

交互链基准（COIN）：当推理遇见具身交互

Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction

University of Science and Technology of China（中国科学技术大学）；Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；Xidian University（西安电子科技大学）；Shanghai Jiao Tong University（上海交通大学）；University of California, Los Angeles（加州大学洛杉矶分校）

Xianhao Wang, Xiaojian Ma, Haozhe Hu, Rongpeng Su, Yutian Cheng, Zhou Ziheng, Hangxin Liu, Lei Liu, Bin Li, Qing Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

COIN基准通过设计日常场景下的50个交互任务，评估机器人在部分可观测环境下进行因果依赖推理的能力，揭示现有方法在交互推理任务中的局限性。

摘要：

通用的具身代理必须执行互动性、因果依赖性的推理，持续与环境互动，获取信息并更新计划以解决长期任务。例如，从柜子中取苹果可能需要打开多个门和抽屉，才能使苹果变得可见和可及，这需要在部分可观测条件下进行顺序交互。然而，现有基准未能系统评估这一关键能力。我们引入COIN基准，通过三个关键贡献来评估现实机器人操作中的交互推理能力：首先，我们构建了COIN-50：50个日常场景交互任务，以及COIN-Primitive所需因果依赖任务和COIN-Composition具有中期复杂度的任务，用于技能学习和泛化评估。其次，我们开发了一种低成本移动AR远程操作系统，并收集了包含50个基础任务演示（共1000个）的COIN-Primitive数据集。第三，我们开发了关于执行稳定性和泛化鲁棒性的系统评估指标，以评估CodeAsPolicy、VLA和语言条件的H-VLA方法。我们的全面评估揭示了当前方法的关键局限性：模型在交互推理任务中面临视觉理解与运动执行之间显著差距的挑战。我们提供了这些局限性的细粒度分析。

英文摘要：

Generalist embodied agents must perform interactive, causally-dependent reasoning, continually interacting with the environment, acquiring information, and updating plans to solve long-horizon tasks before they could be adopted in real-life scenarios. For instance, retrieving an apple from a cabinet may require opening multiple doors and drawers before the apple becomes visible and reachable, demanding sequential interaction under partial observability. However, existing benchmarks fail to systematically evaluate this essential capability. We introduce COIN, a benchmark designed to assess interactive reasoning in realistic robotic manipulation through three key contributions. First, we construct COIN-50: 50 interactive tasks in daily scenarios, and create COIN-Primitive required by causally-dependent tasks, and COIN-Composition with mid-term complexity for skill learning and generalization evaluation. Second, we develop a low-cost mobile AR teleoperation system and collect the COIN-Primitive Dataset with 50 demonstrations per primitive task (1,000 in total). Third, we develop systematic evaluation metrics about execution stability and generalization robustness to evaluate CodeAsPolicy, VLA, and language-conditioned H-VLA approaches. Our comprehensive evaluation reveals critical limitations in current methods: models struggle with interactive reasoning tasks due to significant gaps between visual understanding and motor execution. We provide fine-grained analysis of these limitations.

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。