BeClaude
Research2026-05-12

COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams

Source: Arxiv CS.AI

arXiv:2604.17693v2 Announce Type: replace-cross Abstract: In cooperative teams where agents act in a fixed order and share a single team-level reward (multi-agent language systems, sequential robotic tasks), per-agent credit assignment is under-determined. Critic-based approaches scale poorly as...

arxivpapers