Gricean Cache Sharing for Multi-Agent Collaboration

Existing multi-agent systems rely heavily on natural language for coordination. While flexible, text imposes a strict sequential bottleneck and often transmits redundant tokens, leading to high latency and noise interference. To bypass this limit without incurring the redundancy of naïve broadcasting, we introduce Gricean Cache Sharing, a controllable thought sharing protocol grounded in Grice’s Cooperative Principle. Instead of treating the thought as a monolithic block, our framework reformulates inter-agent communication as a constrained optimization problem. We design a transparent interface that exports only carefully selected thoughts, and give a mechanism analysis in which Top-$k$ saliency minimizes discarded attention mass for fixed scores and a per-block budget. Empirically, our method reduces latency by $3.3\times$ on average (up to $5.0\times$) while matching or exceeding the accuracy of text baselines on 12 of 15 model–benchmark settings. Ablation studies show that the three modules are complementary, with the full combination outperforming every single- and dual-module variant, while the communication budget acts as a smooth accuracy–latency control knob.