Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning

ArXi:2605.17393v1 Announce Type: cross Coordination graphs are a central abstraction in cooperative multi-agent reinforcement learning (MARL), yet existing sparse-graph learners lack a theoretically grounded mechanism to decide which edges should exist and how much information each edge should carry. Current methods rely on heuristic criteria that offer no formal guarantee on the learned topology, and no principled way to allocate different communication capacities to structurally different agent relationships.