研究大模型多智能体系统中的集体错忆现象，揭示其成因并提出有效防御策略。
When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
- 构建MANBENCH基准，测试四种任务中智能体的集体记忆偏差。
- 不同交互协议下错忆率差异显著，最长记忆时长可使错误率提升2.3倍。
- 通过提示词优化和模型对齐，平均降低74.4%的错忆现象，适合安全敏感场景应用。
大型语言模型（LLMs）的发展极大提升了多智能体系统的协作能力，但其在群体互动中易受集体认知偏差影响的问题尚未得到充分研究。本文聚焦于‘曼德拉效应’——即群体因社会影响与内化错误信息而共同误记历史事件的现象，首次系统研究其在基于大模型的多智能体系统中的存在性、成因及缓解方法。为此，我们提出MANBENCH基准，涵盖四种易受该效应影响的任务类型，并采用五种不同角色分工与记忆时长的交互协议进行评估。我们使用多个LLM对智能体进行测试，量化其错忆程度，并分析关键影响因素。进一步提出两类防御策略：提示层（如认知锚定、来源审查）与模型层对齐方法，相较基线平均减少74.40%的曼德拉效应。研究为构建更稳健、伦理对齐的协同多智能体系统提供重要参考。代码与数据集见https://github.com/bluedream02/Mandela-Effect。
原文摘要 · Abstract (English)
Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the susceptibility of agents to collective cognitive biases remains an underexplored issue. A compelling example is the Mandela effect, a phenomenon where groups collectively misremember past events as a result of false details reinforced through social influence and internalized misinformation. This vulnerability limits our understanding of memory bias in multi-agent systems and raises ethical concerns about the potential spread of misinformation. In this paper, we conduct a comprehensive study on the Mandela effect in LLM-based multi-agent systems, focusing on its existence, causing factors, and mitigation strategies. We propose MANBENCH, a novel benchmark designed to evaluate agent behaviors across four common task types that are susceptible to the Mandela effect, using five interaction protocols that vary in agent roles and memory timescales. We evaluate agents powered by several LLMs on MANBENCH to quantify the Mandela effect and analyze how different factors affect it. Moreover, we propose strategies to mitigate this effect, including prompt-level defenses (e.g., cognitive anchoring and source scrutiny) and model-level alignment-based defense, achieving an average 74.40% reduction in the Mandela effect compared to the baseline. Our findings provide valuable insights for developing more resilient and ethically aligned collaborative multi-agent systems. Code and dataset are available at https://github.com/bluedream02/Mandela-Effect.
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。