arXiv AI September 24, 2026 By Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong

Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate

The paper investigates whether complex communication topologies are necessary for effective multi‑agent debate (MAD) among large language models. It demonstrates that a simple random-without-replacement routing policy—where each agent debates with two newly sampled peers each round—consistently improves the accuracy‑cost trade‑off in sparse MAD setups. Additionally, the study shows that lightweight deliberation stopping can further reduce inference costs without sacrificing accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Sep 22

Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate

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 cen...

llms agents

arXiv AI

Sep 1

PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

arXiv:2606.20621v2 Announce Type: replace Abstract: Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often intro...

By Yang Feng, Ziwei Xu, Xia Hu, Fengxiang He

llms agents benchmarks

arXiv Machine Learning

Jul 15

When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

arXiv:2510. 20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasoning and provide effective supervision to superhuman LLMs.

By Yongqiang Chen, Gang Niu, James Cheng, Bo Han, Masashi Sugiyama

llms agents benchmarks

arXiv AI

Jun 2

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

arXiv:2606. 01828v1 Announce Type: cross Abstract: Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation.

By Wanshuang Gou, Zihan Liu

llms agents

arXiv AI

Jun 30

Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning

arXiv:2606. 29425v1 Announce Type: new Abstract: Existing multi-agent debate frameworks suffer from two critical limitations: they rely on static architectures where agent roles and coordination patterns are fixed at design time, and they require instantiating multiple model copies, incurring substantial computational overhead.

By Dayong Liang, Kaisong Gong, Yi Cai, Changmeng Zheng, Xiao-Yong Wei

agents multimodal benchmarks

arXiv AI

Aug 14

Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

arXiv:2608. 12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies.

By Junzhi Li, Peng He, Qirui Ji, Wei Wang, Lixiang Liu, Chuxiong Sun

llms agents benchmarks

One email a morning, machine-written

Related stories

Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate

PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning

Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference