Problem
Research questions and friction points this paper is trying to address.
sparse multi-agent debate
topology control
communication topology
cost-efficiency
reasoning accuracy
Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate
๐ค AI Summary
็ ็ฉถ้่ฟ็ฎๅ็้ๆบๆ ๆพๅ่ทฏ็ฑ็ญ็ฅ๏ผ่ฎฉๆฏไธชไปฃ็ไธไธคไธชๆฐ้ๆ ท็ไธๅๅไผด่พฉ่ฎบ๏ผๆ้ซ็จ็ๅคไปฃ็่พฉ่ฎบ็ๆๆฌๆ็ใ
๐ Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Sparse Multi-Agent Debate
Random Routing
Cost-Efficiency
Deliberation Stopping
๐ Similar Papers
No similar papers found.
