AI 中文总结
该研究针对多智能体记忆仲裁中的记忆关联偏差问题，提出CAMA框架，通过解耦记忆、估计独立证据源数量及主动恢复缺失证据，有效抑制虚假多数，性能优于现有基线方法。
AI 中文摘要
长期多智能体系统会持续积累不同智能体生成的记忆。现有记忆方法通常将检索到的记忆视为独立证据，通过投票或加权方式组合。但在多智能体场景中，这种独立性假设常不成立：不同智能体写入的记忆可能继承同一上游源或共享偏差，导致相关证据被重复计数，形成虚假多数，我们将该失效模式称为“记忆关联偏差”。为解决该问题，我们提出关联感知记忆仲裁（Correlation-Aware Memory Arbitration，CAMA）框架，该框架可联合解耦检索到的记忆并恢复缺失的独立证据。我们将检索到的记忆建模为查询条件下的证据组，结合神经依赖推理与基于来源的符号先验，估计独立证据源的有效数量，从而防止相关记忆形成虚假多数。由于初始检索集合中可能缺失关键独立证据，CAMA还学习了一种序列恢复策略，在做出最终决策前主动检索替代证据或追踪上游源，旨在恢复足够的独立证据以实现可靠仲裁，同时最小化检索成本。在多个基准上的实验表明，我们的方法优于现有最先进的基线方法，可抑制由相关记忆引发的虚假多数。
英文摘要
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting. However, this independence assumption often fails in multi-agent settings: memories written by different agents may inherit the same upstream source or shared bias, causing correlated evidence to be repeatedly counted and creating a false majority. We term this failure mode \textit{Memory Correlation Bias}. To address the issue, we propose the \textbf{C}orrelation-\textbf{A}ware \textbf{M}emory \textbf{A}rbitration (CAMA) framework that jointly decouples retrieved memories and recovers missing independent evidence. We model the retrieved memories as query-conditioned evidence groups and combine neural dependency inference with provenance-based symbolic priors to estimate the effective number of independent evidence sources, thereby preventing correlated memories from forming a false majority. Since critical independent evidence may be absent from the initial retrieval set, \textsc{CAMA} further learns a sequential recovery policy that actively retrieves alternative evidence or traces upstream sources before making the final decision, aiming to recover sufficient independent evidence for reliable arbitration while minimizing retrieval cost. Experiments on multiple benchmarks demonstrate the superiority of our method over the state-of-the-art baseline methods, suppressing false majorities induced by correlated memories.
