arXiv：cs.AI· Dezheng Bao, Sihang Du, Renhong Huang, Zhizhang Yuan, Yifei Sun, Yang Yang·· 6 小时前
TrueMAD：面向多智能体辩论的定向同行互动机制
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
AI 导读
研究者提出 TrueMAD，一种与骨干模型无关的测试时插件，在答案广播与自我修正之间加入一对一的自由形式同行建议，使源智能体针对目标智能体的当前推理给出支持、反驳、改进或追问，且不更新参数。
正文
Abstract:Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring agents to engage with a particular peer claim. As a result, reliable reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous reasoning may persist and degrade final predictions without actionable feedback. We propose TrueMAD, a backbone-agnostic test-time plug-in that introduces one-to-one, free-form peer advice between answer broadcasting and self-revision. Each source agent responds to a target's current reasoning through support, rebuttal, refinement, or further questions, while the target retains control over how to revise. The same mechanism can augment standard MAD and its improved variants without parameter updates. Across AIME, GPQA-Diamond, and TruthfulQA with Qwen3-30B-A3B, TrueMAD improves agent-level and strict-majority accuracy over MAD by 3.62 and 3.52 percentage points on average, while TrueDMAD improves DMAD by 4.72 and 4.06 points, respectively. Analyses at the utterance, agent-transition, and group levels further show more peer-specific deliberation, more correction-oriented revisions, and more favorable consensus dynamics.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18240 [cs.AI] |
| (or arXiv:2610.18240v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18240 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dezheng Bao [view email]
[v1]
Tue, 13 Oct 2026 12:08:38 UTC (395 KB)
来源：arXiv：cs.AI · arxiv.org