mlsanityData to 13 Oct 2026

Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

arXiv 2405.14744 ↗First posted 23 May 2024cs.CYcited by 38

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

Abstract (arXiv)

Large language models (LLMs) have been shown to face hallucination issues due to the data they trained on often containing human bias; whether this is reflected in the decision-making process of LLM Agents remains under-explored. As LLM Agents are increasingly employed in intricate social environments, a pressing and natural question emerges: Can we utilize LLM Agents' systematic hallucinations to mirror human cognitive biases, thus exhibiting irrational social intelligence? In this paper, we probe the irrational behavior among contemporary LLM Agents by melding practical social science experiments with theoretical insights. Specifically, We propose CogMir, an open-ended Multi-LLM Agents framework that utilizes hallucination properties to assess and enhance LLM Agents' social intelligence through cognitive biases. Experimental results on CogMir subsets show that LLM Agents and humans exhibit high consistency in irrational and prosocial decision-making under uncertain conditions, underscoring the prosociality of LLM Agents as social entities and highlighting the significance of hallucination properties. Additionally, the CogMir framework demonstrates its potential as a valuable platform for encouraging more research into the social intelligence of LLM Agents.

Key facts. Cited by 38 papers in the map (data through 13 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 22 of its 64 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

22 of 64 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Character-LLM: A Trainable Agent for Role-Playing16 Oct
  2. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 20

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,348
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,156
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,586
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,170
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,068
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,777
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,365
  10. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,268
  11. 2023AgentBench: Evaluating LLMs as Agentscited by 1,242
  12. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 798
8 more
  1. 2023Extracting Training Data from Diffusion Modelscited by 729
  2. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 586
  3. 2023A Survey of Hallucination in Large Foundation Modelscited by 367
  4. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 357
  5. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 268
  6. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 235
  7. 2023RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Modelscited by 21
  8. 2023Large Language Model (LLM) Bias Index -- LLMBIcited by 14

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 23; 2026: 14.

38 papers.

Sort:

By area:

  1. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  2. 2025Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoningcited by 29
  3. 2025Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agentscited by 26
  4. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  5. 2025LLM Strategic Reasoning: Agentic Study through Behavioral Game Theorycited by 15
  6. 2025Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systemscited by 15
  7. 2025LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactionscited by 15
  8. 2025LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?cited by 15
  9. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  10. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 14
  11. 2025United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theorycited by 10
  12. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systemscited by 7
26 more
  1. 2025Many LLMs Are More Utilitarian Than Onecited by 7
  2. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  3. 2025Reasoning and Behavioral Equilibria in LLM-Nash Games: From Mindsets to Actionscited by 6
  4. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  5. 2025Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanismcited by 5
  6. 2025Ella: Embodied Social Agents with Lifelong Memorycited by 4
  7. 2026Belief in Authority: Impact of Authority in Multi-Agent Evaluation Frameworkcited by 4
  8. 2025Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Enginescited by 3
  9. 2026RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policycited by 3
  10. 2025Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinationscited by 2
  11. 2026Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformationcited by 2
  12. 2026PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?cited by 2
  13. 2026When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systemscited by 2
  14. 2026HumanStudy-Bench: Towards AI Agent Design for Participant Simulationcited by 2
  15. 2026The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scalecited by 2
  16. 2025InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behaviorcited by 1
  17. 2025The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systemscited by 1
  18. 2026LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systemscited by 1
  19. 2024Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Modelscited by 0
  20. 2025Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Servicecited by 0
  21. 2026Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solvingcited by 0
  22. 2026TransportAgents: a multi-agents LLM framework for traffic accident severity predictioncited by 0
  23. 2026Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolutioncited by 0
  24. 2026Validated Hypotheses as a Lens for Human-Likeness Evaluation in AI Agentscited by 0
  25. 2026You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agentscited by 0
  26. 2026Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games
  2. 2025From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation
  3. 2023Do LLM Agents Exhibit Social Behavior?
  4. 2025Computational Basis of LLM's Decision Making in Social Simulation
  5. 2024EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective
  6. 2025The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
  7. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
  8. 2026Communicate-Predict-Act: Evaluating Social Intelligence of Agents