Counterfactual Credit Policy Optimization for Multi-Agent Collaboration 事件

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration arXiv:2603.21563v2 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce Collaborative Credit Policy Optimization (CCPO), an optimizer-agnostic credit assignme