CoCoBench：具身多智能体任务规划协作基准
原标题：CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning
技术动态AI 70
来源：arXiv cs.RO发布时间待核实
arXiv:2608.28266v1 Announce Type: new Abstract: 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.