Selective and Hybrid-State Communication for Latent Multi-Agent Systems

Efficient communication remains a major bottleneck in large language model multi-agent systems. Latent communication reduces repeated natural-language exchange by transferring internal model states between agents, but these transfers remain costly and are typically designed around conventional KV-cache representations. We address this problem from two complementary perspectives. We introduce SelectKV, a boundary-aware method that selectively communicates KV states while protecting inherited context, and HyLaMAS, which extends latent collaboration to hybrid linear-attention models by communicating both KV caches and recurrent states through a shared workspace. Across six benchmarks, SelectKV reduces communicated KV positions and logical KV payload by 9.7–9.9%, with accuracy unchanged on two benchmarks, within one percentage point on three, and six points lower on HumanEval+. Across Qwen3.5 model scales, HyLaMAS reduces decoded output tokens by 53–80% and achieves $1.16\text{--}2.78\times$ speedups relative to text-based multi-agent communication. Together, these methods provide complementary mechanisms for communication-efficient latent multi-agent systems across conventional and hybrid model architectures.