mlsanityData to 7 Oct 2026

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

arXiv 2602.00428 ↗First posted 31 Jan 2026cs.CL cs.AI cs.CRcited by 2

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 37 of its 49 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

37 of 49 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing16 Jan
  2. 2025CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments16 Sep
  3. 2024Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View23 May
  4. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View3 Oct
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May
  6. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 31

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  11. 2025Gemma 3 Technical Reportcited by 1,686
  12. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
19 more
  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  4. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  5. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  6. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
  7. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  8. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  9. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 107
  10. 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agentscited by 92
  11. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 84
  12. 2025Do as We Do, Not as You Think: the Conformity of Large Language Modelscited by 48
  13. 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systemscited by 45
  14. 2024Conformity in Large Language Modelscited by 30
  15. 2023Integration of Large Language Models and Federated Learningcited by 28
  16. 2024Post-Training Attribute Unlearning in Recommender Systemscited by 23
  17. 2025Memory-Efficient Federated Fine-Tuning of Large Language Models via Layer Pruningcited by 5
  18. 2025Elastic Mixture of Rank-Wise Experts for Knowledge Reuse in Federated Fine-Tuningcited by 5
  19. 2025Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stagescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memorycited by 0
  2. 2026StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
  2. 2026How memory can affect collective and cooperative behaviors in an LLM-Based Social Particle Swarm
  3. 2025Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
  4. 2025Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
  5. 2025Group size effects and collective misalignment in LLM multi-agent systems
  6. 2025Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation
  7. 2026Multi-Agent Consensus as a Cognitive Bias Trigger in Human-AI Interaction
  8. 2026The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions