AI RESEARCH
COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
arXiv CS.AI
•
ArXi:2603.00349v2 Announce Type: replace Many complex tasks require extended effort, diverse capabilities, or coordinated actions beyond what a single agent can provide. However, simply adding agents does not guarantee better performance, as effective cooperation depends on how agents interact with each other and with task structure to satisfy evolving constraints over time. This challenge is amplified for LLM-based multi-agent systems (LLM-MAS): plans, messages, and revisions occur in natural language, whereas task progress depends on grounded environment actions.