Newest papers

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

Ziyi Jiao, Heng Zhang, Drishti Regmi, Xiaokang Ye, Lianhui Qin, Peter Yichen Chen · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31511 · cited by 0 works (OpenAlex) · open-access PDF

Korean

요리 작업에서 두 플레이어를 조정하는 것은 시각 언어 에이전트가 변화하는 장면 상태, 시퀀스 조리 단계를 추적하고 시간 예산에 따라 공유 자원을 할당하는 것을 요구합니다. 우리는 코딩 에이전트를 사용하여 구축 된 Unreal Engine 환경에서 이러한 기능을 평가하기위한 Overcooked-영감을받은 벤치마크를 도입합니다. 단일 시각 언어 모델은 상단 시각 관찰에서 플레이어를 모두 제어하고 엔진이 탐색을 실행하는 동안 높은 수준의 행동을 선택합니다. 벤치마크는 5 개의 범주에 20 개의지도를 포함합니다. 이러한 범주는 장비 컨테이너, 지형 변경 및 핸드오프 의존성을 사용하여 중앙 조정의 평가를 지원합니다. Prop legend 및

Machine translation (Meta M2M100); the English original follows.

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, selecting high-level actions while the engine executes navigation. The benchmark contains 20 maps in five categories. These categories support evaluation of centralized 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. The evaluation compares four VLMs on all 20 maps, measuring task score, order completion, delivery precision, action acceptance rate, and model API expenditure. A memory ablation on the same 20 maps examines the effect of a shared, self-authored notebook while retaining six-response action history in both conditions. The strongest evaluated model, \texttt{gpt-6-astra}, achieves 26.2\% mean order completion. Notebook memory has mixed score effects across models, with positive mean differences for Claude and Qwen and negative differences for GPT and Gemini.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Benchmark (surveying), Computer science, Task (project management), Handover, Coding (social sciences), Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange