arXiv cs.MA· Dianzhi Yu, Hongru Wang, Ziheng Xiong, Yanyu Chen, Zixing Song, Jianting Chen, Zhenfei Yin, Jeff Z. Pan, Amos Storkey, Irwin King·· 17 小时前AI 评分42
多智能体社交网络中的虚假信念传播、持续与缓解：以曼德拉效应为视角
False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect
AI 导读
研究构建了连接智能体通信、私有记忆与共享模拟网络的控制框架，用覆盖 8 个领域、4 个可信度等级的 540 条虚构声明测试多智能体社交网络中的虚假信念动态。结果显示被测模型轻易接受并传播虚构声明，传播触达率最高达 96.0%，且传播速度受通信拓扑影响；撤回发布者后接受度几乎不下降，针对性纠正干预优于预防措施但无法消除虚假信念。
正文 · 原文
Abstract:Multi-agent social networks are emerging as communities in which agents communicate, retain memories, and publish information that others can find as evidence. These interactions create opportunities for false claims to spread and remain influential beyond their original sources, analogous to the Mandela effect in human societies, in which many people recall the same false memory. In this paper, we systematically study false-belief dynamics through the lens of the Mandela effect, focusing on dissemination, persistence, and mitigation. Specifically, we build a controlled framework connecting agent communication, private memory, and a shared simulated web to mimic information dissemination in practical social networks, supported by 540 fabricated claims spanning 8 domains and 4 plausibility levels. For dissemination, we measure how widely and quickly claims gain acceptance across models and communication topologies. For persistence, we withdraw agents promoting fabricated claims while retaining existing articles and memories, and track subsequent acceptance. For mitigation, we compare preventive measures applied before implantation with corrective interventions introduced after claims have spread. Experimental results show that evaluated models readily accept and disseminate fabricated claims, with dissemination reach as high as 96.0%. Dissemination reach varies with claim plausibility, domain, and network size and composition, while communication topology shapes dissemination speed across model families. Acceptance barely declines after fabricators withdraw, and targeted corrective interventions outperform the preventive measures without eliminating false beliefs. These findings identify persistent false beliefs as a safety challenge for multi-agent social networks and highlight the need to address both their initial dissemination and the accumulated evidence that sustains them.
| Comments: | 39 pages, 6 figures, 13 tables |
| Subjects: | Social and Information Networks (cs.SI); Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.33026 [cs.SI] |
| (or arXiv:2610.33026v1 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33026 arXiv-issued DOI via DataCite |
Submission history
From: Dianzhi Yu [view email]
[v1]
Sun, 11 Oct 2026 06:49:02 UTC (3,059 KB)
来源：arXiv cs.MA · arxiv.org