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

• URL: http://arxiv.org/abs/2602.00428v1
• Date: Sat, 31 Jan 2026 00:47:46 GMT
• Title: When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
• Abstract summary: Mandela effect is a phenomenon where groups collectively misremember past events as a result of false details reinforced through social influence and internalized misinformation.<n>This vulnerability limits our understanding of memory bias in multi-agent systems and raises ethical concerns about the potential spread of misinformation.<n>We propose strategies to mitigate this effect, including prompt-level defenses and model-level alignment-based defense.
• Score: 45.33522933253109
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems [103.90831279037094]
  LLM-based multi-agent trading systems are moving rapidly from research prototypes to live deployments that control real assets.<n>A corrupted signal can propagate to the final decision and translate into realized financial loss.<n>We present the first systematic empirical study in the financial domain to characterize how an adversarial signal enters a multi-agent trading system.
  arXiv  Detail & Related papers  (2026-08-25T05:07:37Z)
• Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation [8.478223327809527]
  This study specifically analyzes the impact of cognitive heterogeneity on agent interactions.<n>We employ DeepSeek and GPT agents to systematically vary reasoning sophistication across supply chain tiers.<n>Results indicate that agents exhibit myopic and self-interested behaviors that exacerbate systemic inefficiencies.
  arXiv  Detail & Related papers  (2026-04-19T03:03:25Z)
• How memory can affect collective and cooperative behaviors in an LLM-Based Social Particle Swarm [0.0]
  This study examines how model-specific characteristics of Large Language Model (LLM) agents, including internal alignment, shape the effect of memory on their collective and cooperative dynamics in a multi-agent system.
  arXiv  Detail & Related papers  (2026-04-14T03:54:49Z)
• The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems [20.359327253718718]
  Bias in large language models (LLMs) remains a persistent challenge, manifesting in stereotyping and unfair treatment across social groups.<n>We study how internal specialization, underlying LLMs and inter-agent communication protocols influence bias robustness, propagation, and amplification.<n>Our findings highlight critical factors shaping fairness and resilience in multi-agent LLM systems.
  arXiv  Detail & Related papers  (2025-10-13T02:56:42Z)
• CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards [80.78748457530718]
  Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining.<n>We introduce Co-Evolving Multi-Agent Systems (CoMAS), a novel framework that enables agents to improve autonomously by learning from inter-agent interactions.
  arXiv  Detail & Related papers  (2025-10-09T17:50:26Z)
• Can an Individual Manipulate the Collective Decisions of Multi-Agents? [53.01767232004823]
  M-Spoiler is a framework that simulates agent interactions within a multi-agent system to generate adversarial samples.<n>M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples.<n>Our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems.
  arXiv  Detail & Related papers  (2025-09-20T01:54:20Z)
• An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring [8.779871128906787]
  We introduce a general and adversary-resistant multi-agent LLM framework based on credibility scoring.<n>Our system associates a credibility score that is used when aggregating the team outputs.
  arXiv  Detail & Related papers  (2025-05-30T05:57:37Z)
• Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness [50.29739337771454]
  Multi-agent debate (MAD) approaches offer improved reasoning, robustness, and diverse perspectives over monolithic models.<n>This paper conceptualizes MAD as a test-time computational scaling technique, distinguished by collaborative refinement and diverse exploration capabilities.<n>We conduct a comprehensive empirical investigation comparing MAD with strong self-agent test-time scaling baselines on mathematical reasoning and safety-related tasks.
  arXiv  Detail & Related papers  (2025-05-29T01:02:55Z)
• Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems [7.140644659869317]
  We investigate the dynamics of peer influence in multi-agent systems based on Large Language Models (LLMs)<n>We show that the gap between self-confidence and perceived confidence in peers significantly impacts an agent's likelihood to conform.<n>We find that the format in which peer information is presented plays a critical role in modulating the strength of herd behavior.
  arXiv  Detail & Related papers  (2025-05-27T12:12:56Z)
• How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior [65.70584076918679]
  Memory is a critical component in large language model (LLM)-based agents.<n>This paper studies how memory management choices impact the LLM agents' behavior, especially their long-term performance.
  arXiv  Detail & Related papers  (2025-05-21T22:35:01Z)
• HiddenBench: Assessing Collective Reasoning in Multi-Agent LLMs via Hidden Profile Tasks [12.203366267017737]
  We introduce HiddenBench, the first benchmark for evaluating collective reasoning in multi-agent LLMs.<n>To ground the benchmark, we formalize the paradigm with custom tasks and show that GPT-4.1 groups fail to integrate distributed knowledge.<n>We then construct the full benchmark, spanning 65 tasks drawn from custom designs, prior human studies, and automatic generation.
  arXiv  Detail & Related papers  (2025-05-15T19:22:54Z)
• Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities [28.244283407749265]
  We investigate the security implications of large language models (LLMs) in multi-agent systems. We propose a novel two-stage attack method involving Persuasiveness Injection and Manipulated Knowledge Injection. We demonstrate that our attack method can successfully induce LLM-based agents to spread both counterfactual and toxic knowledge.
  arXiv  Detail & Related papers  (2024-07-10T16:08:46Z)
• Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL [107.58821842920393]
  We quantify the agent's behavior difference and build its relationship with the policy performance via bf Role Diversity We find that the error bound in MARL can be decomposed into three parts that have a strong relation to the role diversity. The decomposed factors can significantly impact policy optimization on three popular directions.
  arXiv  Detail & Related papers  (2022-06-01T04:58:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.