我们需要复杂的拓扑控制吗？不同对等体随机路由提高稀疏多智能体辩论的成本效益
Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate
- University of Liverpool（利物浦大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究探讨稀疏多智能体辩论中是否需要复杂拓扑控制，发现简单的无放回随机路由策略即可显著改善成本效益，并验证轻量级停止机制可降低推理成本，提示复杂拓扑控制需与简单基线对比评估。
AI中文摘要：
多智能体辩论（MAD）已成为通过迭代对等交互提高大型语言模型（LLMs）推理准确性的有前景范式。通信拓扑在此过程中发挥核心作用，促使越来越复杂的机制被设计出来，以学习、适应或动态重新配置智能体交互，从而提高准确性或推理可靠性。与此同时，先前研究表明，更简单的稀疏通信已经可以在显著降低成本的条件下实现有竞争力的性能。在本工作中，我们更仔细地审视稀疏MAD，并探讨复杂的拓扑控制是否真的有必要以改善集体推理。我们发现，一种简单的无放回随机路由策略——即每轮让每个智能体与两个不同的、新采样的对等体进行辩论——提供了一个令人惊讶的强基线，并持续改善稀疏MAD的准确性-成本权衡。基于这一观察，我们进一步研究辩论停止机制，并表明轻量级停止可以大幅降低推理成本，同时保持有竞争力的准确性。我们的结果表明，诸如学习式拓扑适应等复杂的拓扑控制，应在额外的复杂性被证明合理之前，与强大的简单路由和停止基线进行评估。
英文摘要：
Multi-agent debate (MAD) has emerged as a promising paradigm for improving the reasoning accuracy of large language models (LLMs) through iterative peer interaction. Communication topology plays a central role in this process, motivating increasingly sophisticated mechanisms that learn, adapt, or dynamically reconfigure agent interactions to improve accuracy or reasoning reliability. Meanwhile, prior studies suggest that much simpler sparse communication can already achieve competitive performance at substantially lower cost. In this work, we take a closer look at sparse MAD and ask whether complex topology control is actually necessary to improve collective reasoning. We find that a simple random-without-replacement routing policy, which lets each agent debate with two distinct and newly sampled peers at every round, provides a surprisingly strong baseline and consistently improves the accuracy-cost trade-off of sparse MAD. Building on this observation, we further study deliberation stopping and show that lightweight stopping can substantially reduce inference cost while preserving competitive accuracy. Our results suggest that sophisticated topology control such as learned topology adaption should be evaluated against strong simple routing and stopping baselines before its additional complexity is justified.
