# 延迟验证破坏多智能体LLM信念：不稳定性阈值与最优校正器放置

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-25 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmr15rjld003gslh4qxx3e2aq
- 原文链接：https://arxiv.org/abs/2606.27409

## AI 摘要

多智能体大语言模型系统中，验证器与批评者智能体存在延迟，导致虚假声明在延迟期间通过网络传播。该过程被建模为带接地校正器节点图上的延迟共识，通过接地拉普拉斯矩阵谱分解得到校正剂量的闭合形式稳定性阈值：过强或过延迟的校正会使共识转变为振荡。通信与验证延迟重合时系统最不稳定；延迟为2时阈值是黄金分割率倒数。同一框架给出超模放置目标及贪婪(1-1/e)近似规则，用于将有限校正器预算分配给影响力节点。五个开放模型上的实验确认了剂量‑延迟振荡，而接地事实性回答使真相成为吸收边界从而消除该效应。

## 正文

Multi-agent large language model (LLM) systems often rely on verifier and critic agents to suppress hallucinations, but verification is delayed. During this delay, false claims can propagate through the agent network. We model this process as delayed consensus on a graph with grounded corrector nodes. Spectral decomposition by the grounded Laplacian yields a closed-form stability threshold for the verification dose: correction that is too strong or too delayed can turn consensus into oscillation. The most unstable regime occurs when the communication and verification delays coincide; for delay two, the threshold is the inverse golden ratio. The same framework gives a supermodular placement objective and a greedy (1-1/e)-approximation rule for assigning a limited corrector budget to influential nodes. Experiments across five open models confirm the predicted dose-delay oscillations. By contrast, grounded factual answering makes truth an absorbing boundary and eliminates the effect, suggesting that the instability is specific to signed-belief tasks while grounded verification remains stabilizing