Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning

ArXi:2512.11179v3 Announce Type: replace Graph-based multi-agent reinforcement learning (MARL) enables coordinated behavior under partial observability by modeling agents as nodes and communication links as edges. While recent methods excel at learning sparse coordination graphs-determining who communicates with whom-they do not address what information should be transmitted under hard bandwidth constraints. We study this bandwidth-limited regime and show that naive dimensionality reduction consistently degrades coordination performance.