动态调整角色与连接，让多智能体辩论更公平可靠。
PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate
- 根据智能体状态动态重分配角色和通信结构。
- 在四个推理基准上平均准确率超越最强基线。
- 适合追求模型可靠性与公平性的研究者使用。
多智能体辩论通过迭代同行批评提升大语言模型的可靠性。然而固定拓扑常引入持久的位置偏见，放大不可靠智能体，并对角色分配高度敏感。我们提出 extit{Permutation-Equivariant Adaptive Routing Multi-Agent Debate (PEAR)}，一种无需训练的推理时协议，可动态重构连续辩论回合中的通信角色与稀疏拓扑。通过基于智能体状态演变的战略性角色切换，PEAR防止任何智能体长期占据优势网络位置，或更均衡地分配影响力。我们从理论上将PEAR刻画为等变稀疏路由：在智能体重标签下保持精度的同时，降低路由复杂度并提升泛化能力。在四个推理基准和六种不同LLM主干上的全面实证评估表明，PEAR显著提升平均准确率，超越最强辩论基线。代码已开源：https://github.com/EVIEHub/PEAR。
原文摘要 · Abstract (English)
Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduce persistent positional biases, amplify unreliable agents, and cause high sensitivity to role assignments. We introduce \textit{Permutation-Equivariant Adaptive Routing Multi-Agent Debate (PEAR)}, an inference-time train-free protocol that dynamically reconfigures communication roles and sparse topologies across consecutive debate rounds. By strategically switching agent-to-role assignments based on evolving agent states, PEAR prevents any agent from permanently occupying a privileged network position or distributes influence more evenly across the debate. We theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization. Comprehensive empirical evaluations across four reasoning benchmarks and six diverse LLM backbones demonstrate PEAR significantly improves average accuracy over the strongest debate baselines. The code is available at https://github.com/EVIEHub/PEAR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。