NegoLat: Negotiating What to Communicate in Multi-Agent Systems

A central yet under-explored question in multi-agent systems (MAS) is what to communicate. Existing protocols, whether textual or latent, remain sender-centric: an upstream agent composes one message from its own context and delivers the same payload to every downstream agent, which participates only after the message has been formed. Such one-shot communication mismatches receivers that need different information and leaves incomplete or conflicting messages unrepaired. We propose NegoLat, a training-free receiver-negotiated latent communication paradigm. On each edge, the sender first exposes a semantic probe; the downstream receiver audits it against its own role and selectively requests refinement; the sender then regenerates a receiver-specific message only for those who asked. We further analyze when receiver-guided regeneration is beneficial and how a bounded request budget affects information coverage. Across ten benchmarks spanning mathematical reasoning, code generation, and visual question answering, NegoLat consistently outperforms text-based and fixed latent communication, improving over the best baseline by $+1.07$ pp (Qwen3-4B-Instruct) and $+2.47$ pp (Qwen3-VL-4B) on average under Hierarchical MAS, with limited overhead. Communication analyses show that NegoLat adaptively adjusts transmitted information according to downstream requirements. Code will be released.