延迟验证会引发多智能体信念系统震荡，关键在于纠正力度与延迟的平衡。
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
- 用图的拉普拉斯谱分解建模验证延迟下的共识过程
- 当通信与验证延迟相等时系统最不稳定，阈值为黄金分割倒数
- 提出最优纠正节点部署策略，适用于高影响力节点资源有限场景
多智能体大语言模型系统常依赖验证者和批评者来抑制幻觉，但验证存在延迟。在此延迟期间，错误信息可在智能体网络中传播。本文将该过程建模为带接地纠正节点的图上延迟共识问题。通过接地拉普拉斯矩阵的谱分解，推导出验证剂量的闭式稳定阈值：纠正过强或过迟均可能导致共识转为振荡。最不稳定的状况出现在通信延迟与验证延迟一致时；当延迟为2时，阈值为黄金分割的倒数。该框架同时给出超模的纠正节点布置目标，并提供贪婪(1-1/e)近似算法，用于在有限纠正预算下分配至关键节点。五种开源模型的实验验证了预测的剂量-延迟振荡现象。相比之下，基于事实的直接回答使真相成为吸收态，消除该效应，表明此类不稳定性仅存在于符号信念任务中，而接地验证本身仍具稳定性。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。