When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Decentralized Communication Policy for Multi Agent Multi Armed Bandit Problems
This paper proposes a novel policy for a group of agents to, individually as well as collectively, solve a multi armed bandit (MAB) problem. The policy relies solely on the information that an agent has obtained through …
Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning
Multi-agent deep reinforcement learning (MADRL) problems often encounter the challenge of sparse rewards. This challenge becomes even more pronounced when coordination among agents is necessary. As performance depends no…
Deep Reinforcement LearningThe AI Memory Gap: Users Misremember What They Created With AI or Without
As large language models (LLMs) become embedded in interactive text generation, disclosure of AI as a source depends on people remembering which ideas or texts came from themselves and which were created with AI. We inve…
Text GenerationSafety is Non-Compositional: A Formal Framework for Capability-Based AI Systems
This paper contains the first formal proof that safety is non-compositional in the presence of conjunctive capability dependencies: two agents each individually inca- pable of reaching any forbidden capability can, when …
Epidemic Modeling with Generative Agents
This study offers a new paradigm of individual-level modeling to address the grand challenge of incorporating human behavior in epidemic models. Using generative artificial intelligence in an agent-based epidemic model, …
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model