1
More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
揭示一个反直觉现象：更强大的LLM反而在零成本协作中更容易失败，挑战多智能体合作假设。
arXiv:2604.07821v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly coordinate in multi-agent systems, yet we lac…