Saved in:
Bibliographic Details
Main Authors: Wang, Xianhao, Ma, Xiaojian, Hu, Haozhe, Su, Rongpeng, Cheng, Yutian, Ziheng, Zhou, Liu, Hangxin, Liu, Lei, Li, Bin, Li, Qing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913042354143232
author Wang, Xianhao
Ma, Xiaojian
Hu, Haozhe
Su, Rongpeng
Cheng, Yutian
Ziheng, Zhou
Liu, Hangxin
Liu, Lei
Li, Bin
Li, Qing
author_facet Wang, Xianhao
Ma, Xiaojian
Hu, Haozhe
Su, Rongpeng
Cheng, Yutian
Ziheng, Zhou
Liu, Hangxin
Liu, Lei
Li, Bin
Li, Qing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16886
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction
Wang, Xianhao
Ma, Xiaojian
Hu, Haozhe
Su, Rongpeng
Cheng, Yutian
Ziheng, Zhou
Liu, Hangxin
Liu, Lei
Li, Bin
Li, Qing
Robotics
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.
title Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction
topic Robotics
url https://arxiv.org/abs/2604.16886