跳到正文
arXiv cs.AI· Ziyi Jiao, Heng Zhang, Drishti Regmi, Xiaokang Ye, Lianhui Qin, Peter Yichen Chen·· 10 小时前AI 评分31

DuoCook:受 Overcooked 启发的视觉规划与协作基准

DuoCook: An Overcooked-Inspired Benchmark for Visual Planning and Coordination

AI 导读

DuoCook 是一个受 Overcooked 启发、在 Unreal Engine 环境中构建的视觉规划与双人协作基准,包含五大类共 20 张地图,由单个视觉语言模型通过每名玩家独立的决策调用同时控制两名玩家。

正文 · 原文

View PDF HTML (experimental)

Abstract:Coordinating two players in a cooking task requires a vision-language agent to track changing scene states, sequence recipe steps, and allocate shared resources under a time budget. We introduce an Overcooked-inspired benchmark for evaluating these capabilities in Unreal Engine environments constructed using coding agents. A single vision-language model controls both players from top-down visual observations \rev{through separate per-player decision calls}, selecting high-level actions \rev{and image-labeled target cells} while the engine executes navigation. The benchmark contains 20 maps in five categories. These categories support evaluation of \rev{two-player} coordination under equipment contention, changing terrain, and handoff dependencies. A prop legend and pot ingredient-count indicators provide explicit visual cues, while grid-based destinations support spatial grounding\rev{; text gives no station coordinates, so target locations come mainly from the image}. The evaluation compares \rev{five VLMs and a privileged scripted reference policy on all 20 maps}, measuring task score, order completion, delivery precision, \rev{aim accuracy}, and model API expenditure. \rev{Two paired ablations on all 20 maps toggle a shared self-authored notebook and reduce the textual prompt from about 3,600 to about 440 words while keeping the images fixed.} \rev{The strongest model completes 35\% of orders and exceeds the scripted reference, which has ground-truth station access; the notebook's effect is mixed in sign and not statistically reliable, and reducing the prompt text lowers the score of two models while leaving the other three nearly unchanged.} Together, the environment design and evaluation protocol provide a framework for investigating how visual state tracking and task scheduling contribute to coordinated cooking behavior.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2610.31511 [cs.AI]
  (or arXiv:2610.31511v2 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2610.31511

arXiv-issued DOI via DataCite

Submission history

From: Heng Zhang [view email]
[v1] Thu, 22 Oct 2026 16:26:38 UTC (24,602 KB)
[v2] Wed, 18 Nov 2026 15:34:45 UTC (24,492 KB)

来源:arXiv cs.AI · arxiv.org