AI RESEARCH
CoFi-PGMA: Counterfactual Policy Gradients under Filtered Feedback for Multi-Agent LLMs
arXiv CS.LG
•
ArXi:2604.22785v1 Announce Type: new Large language model (LLM) deployments increasingly rely on multi-agent architectures in which multiple models either compete through routing mechanisms or collaborate to produce a final answer. In both settings, the learning signal received by each agent is filtered by the system mechanism. Routing produces selection-gated feedback where only the chosen response is evaluated, while collaboration produces shared rewards that obscure the individual contribution of each agent.