Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

About

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 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 at https://github.com/EVIEHub/PEAR.

Yang Feng, Ziwei Xu, Xia Hu, Fengxiang He• 2026

Related benchmarks

TaskDatasetResultRank
Multitask Language UnderstandingMMLU-Pro
Accuracy80.5
303
Grade School Math ReasoningGSM8K
Accuracy (GSM8K)98
186
FactualityTruthfulQA
Accuracy91.5
145
Competition Mathematical ReasoningMATH 500
Accuracy66.5
48
Question AnsweringTruthfulQA (full dataset)
Accuracy86.8
14
Showing 5 of 5 rows

Other info

Follow for update