Abstract:Multi-Agent Debate (MAD) improves LLM-agent accuracy but suffers from rapid context growth, limiting scalability in larger multi-agent settings. Existing methods prune low-utility communications using prior signals, such as token-level log-likelihoods or LLM self-reported confidence. However, these signals become unreliable under hallucination, degrading the accuracy of MAD methods that rely on them. We propose SVR-MAD, a Bayesian-inspired MAD framework that treats pre-debate signals as priors and debate outcomes as posterior-style evidence for estimating agent correctness. SVR-MAD uses this evidence to incrementally construct the communication graph, prioritizing agents whose answers survive peer challenges. Experiments across multiple LLMs and benchmarks show that SVR-MAD reduces token cost by up to 61% while matching or improving accuracy relative to the most accurate competing MAD baseline.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2605.23099 [cs.MA] |
| (or arXiv:2605.23099v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2605.23099 arXiv-issued DOI via DataCite (pending registration) |
From: Weifan Jiang [view email]
[v1]
Thu, 21 May 2026 23:17:03 UTC (65 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。