RhyCo: Rhythm-Controlled Coordination for Multi-Agent LLM Reasoning

In current multi-agent LLM systems, orchestration happens only between turns, so an inactive agent has no structured channel to intervene before being scheduled, even when it could provide decisive evidence that the ongoing reasoning has gone wrong. We name the missing property communication rhythm: the ability to listen, stay silent, and proactively intervene at a self-adaptive pace, as effective teams do. We propose RhyCo (Rhythm-Controlled Coordination), a framework that adds communication rhythm to multi-agent systems (MAS) by moving orchestration inside the turn. RhyCo introduces a dual-channel speaker-listener interface that while the speaker streams reasoning chunks, each listener exposes a probabilistic signal at every chunk and decodes a compact structured whisper only on escalation. A two-tier orchestrator then decides whether to stay silent, retain the speaker, or hand control to a listener, with an MLP gate handling routine chunks and an LLM arbitrator engaged only on escalation. Experiments show that unrestricted listener intervention can degrade MAS performance, while RhyCo turns the same proactive capability into consistent gains on math, code, and multi-hop benchmarks. On MATH-L5, RhyCo-Base uses about $1.2\times$ the output tokens of a single agent and RhyCo-RL uses about $3.3\times$, compared to $7.8\times$ for Multi-Agent Debate and $5.7\times$ for Self-Consistency at five samples.