Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe bandwidth constraints. Many communication architectures still expose a coupled bottleneck in which a shared latent representation is used for both policy execution and inter-agent communication. Consequently, reducing message size directly limits the policy's latent space, often leading to significant performance degradation. We address this with two contributions. First, we introduce $β$, a normalised per-agent bandwidth budget that unifies sparsity, rounds, and message dimension into a single comparable constraint. Second, we provide SLIM, a minimal architecture that decouples the communication pathway from the policy's latent representation, allowing us to isolate the effect of bandwidth from the effect of policy capacity while benefiting from in-step communication. We evaluate our method on several partially-observable MARL benchmarks, where communication is essential. Our approach achieves state-of-the-art performance and exhibits scalability and robustness under limited communication, with only marginal degradation as bandwidth is reduced.

翻译：通信在多智能体强化学习中促进协作，但许多实际应用（例如无人机群执行搜索与救援任务）运行在严格的带宽约束下。现有通信架构仍存在耦合瓶颈，即共享的潜在表示同时用于策略执行与智能体间通信。因此，缩减消息大小会直接限制策略的潜在空间，常导致性能显著下降。我们通过两项贡献解决此问题：首先，引入归一化的每智能体带宽预算$β$，将稀疏性、通信轮次与消息维度统一为单一可比约束；其次，提出最小化架构SLIM，将通信路径与策略的潜在表示解耦，从而在享受同步通信优势的同时，分离带宽影响与策略容量影响。我们在多个需通信的部分可观测多智能体强化学习基准上评估该方法，其在有限通信下实现了最先进性能，并展现出可扩展性与鲁棒性，带宽降低时性能仅出现轻微下降。