Semantic Information-bottleneck Guided Multi-Agent Communication Learning

Multi-agent reinforcement learning relies critically on inter-agent communication for effective coordination in partially observable environments. Recent work has pursued either information-theoretic compression for efficiency or language grounding for interpretability, yet neither addresses the fundamental relationship between what information to communicate and how precisely to communicate it. To address this gap, we introduce **S**emantic **I**nformation-bottleneck **G**uided **M**ulti-**A**gent communication (SIGMA), a framework combining these two perspectives through the variance parameter $\sigma$ of a variational communication encoder. SIGMA uses $\sigma$ to quantify uncertainty from partial observability and to weight messages in Bayesian fusion, while a KL regularizer guides the latent space during pretraining; at execution, information flow is governed by confidence-weighted fusion. Concretely, SIGMA leverages a one-time LLM annotation of a small set of real observations to pretrain a semantically structured latent space; agents then transmit distribution parameters from this space conditioned on their local views, and the encoder is jointly optimized with the policy network, allowing $\sigma$ to weight messages by confidence. Empirically, on standard MARL benchmarks, SIGMA achieves strong performance, remains robust under reduced communication budgets, and transfers effectively to unseen tasks.