Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. However, existing multi-agent debate and collaboration frameworks typically adopt fully connected communication, causing the number of messages, token costs, and end-to-end latency to grow approximately quadratically with the number of agents; although fixed sparse topologies reduce overhead, they cannot adapt communication relationships to different task instances or intermediate reasoning states, making them prone either to preserving low-value interactions or to losing critical error-correction information. To address this problem, this paper proposes DySCo (Dynamic Sparse Consensus), a dynamic trust-aware sparse consensus mechanism. In each round of reasoning, DySCo estimates the value of communication edges based on agent reliability, answer divergence, and task relevance, and selects a small number of high-value edges for message exchange under budget constraints; it then aggregates the answers of different agents through dynamic trust weights and terminates the discussion early once consensus stabilizes. This mechanism replaces universal broadcasting with on-demand communication, thereby reducing communication overhead while preserving essential cross-validation information. We further present analyses of communication complexity and consensus stability, and evaluate the performance of DySCo on mathematical reasoning, logical reasoning, and factual question-answering tasks.

翻译：大语言模型驱动的多智能体系统通过多轮辩论、角色专业化和交叉验证提升了复杂推理任务的可靠性。然而，现有的大语言模型多智能体辩论与协作框架通常采用全连接通信方式，导致消息数量、令牌成本和端到端延迟随智能体数量近似呈二次方增长；尽管固定稀疏拓扑可降低开销，但其无法根据不同的任务实例或中间推理状态调整通信关系，容易造成保留低价值交互或丢失关键纠错信息的问题。针对这一问题，本文提出DySCo（动态稀疏共识），一种基于动态信任的稀疏共识机制。在每轮推理中，DySCo基于智能体可靠性、答案分歧度和任务相关性估计通信边的价值，并在预算约束下选择少量高价值边进行消息交换；随后通过动态信任权重聚合不同智能体的答案，并在共识稳定后提前终止讨论。该机制以按需通信替代全局广播，从而在降低通信开销的同时保留关键交叉验证信息。我们进一步给出了通信复杂度与共识稳定性的理论分析，并在数学推理、逻辑推理和事实问答任务上评估了DySCo的性能。