TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
This addresses the problem of evaluating generalizable multi-modal collaborative agents for researchers, but it is incremental as it builds on existing benchmarks and methods.
The authors introduced TeamCraft, a benchmark for multi-modal multi-agent systems in Minecraft with 55,000 task variants, to evaluate collaborative agents, finding that existing models struggle with generalization to novel goals, scenes, and agent numbers.
Collaboration is a cornerstone of society. In the real world, human teammates make use of multi-sensory data to tackle challenging tasks in ever-changing environments. It is essential for embodied agents collaborating in visually-rich environments replete with dynamic interactions to understand multi-modal observations and task specifications. To evaluate the performance of generalizable multi-modal collaborative agents, we present TeamCraft, a multi-modal multi-agent benchmark built on top of the open-world video game Minecraft. The benchmark features 55,000 task variants specified by multi-modal prompts, procedurally-generated expert demonstrations for imitation learning, and carefully designed protocols to evaluate model generalization capabilities. We also perform extensive analyses to better understand the limitations and strengths of existing approaches. Our results indicate that existing models continue to face significant challenges in generalizing to novel goals, scenes, and unseen numbers of agents. These findings underscore the need for further research in this area. The TeamCraft platform and dataset are publicly available at https://github.com/teamcraft-bench/teamcraft.