Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows

Excerpt

arXiv:2604.20658v2 Announce Type: replace Abstract: Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solving. These systems require agents to coordinate under shared constraints, such as GPUs or credit balances, where cooperative behavior matters. Behavioral economics provides a rich toolkit of games that isolate distinct cooperation mechanisms, yet it remains unknown whether a model's behavior in th