CoCoBench: 具現化マルチエージェントタスク計画のための協調調整ベンチマーク
CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning
マルチエージェントの協調失敗を細かく診断できるベンチマークCoCoBenchを提案し、897の検証済みインスタンスで4種類の協調構造を評価する。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yang Chen, Ye-Xin Xie, Lirong Che, Danyang Peng, Yuzhe Yang, Peiwen Lin, Xu Cao, Chuang Wang, Lei Yuan, Jian Su, Lan-Zhe Guo
分類: cs.RO
原文アブストラクト
Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still lack fine-grained diagnostics for multi-agent coordination. Most benchmarks either focus on single-agent task completion or summarize multi-agent behavior with overall task success rates, which can obscure coordination failures such as duplicated work, violations of ordering constraints, resource contention, and desynchronized handoffs. In this paper, we introduce CoCoBench, a construct-level benchmark for evaluating multi-agent embodied coordination in executable household tasks. CoCoBench contains 897 oracle-validated instances organized around four recurring coordination constructs: task allocation, sequential ordering, mutual exclusion, and handoff coordination. In addition to task success rate, CoCoBench provides construct-level scores that measure whether agents coordinate effectively. We evaluate 11 leading MLLMs across different coordination modes, observation inputs, and numbers of agents. The results show that coordination ability is highly construct-specific: strong overall performance does not imply balanced competence across different coordination types. These findings point to new directions for designing targeted model architectures and improving multi-agent coordination ability.