mlsanityData to 14 Oct 2026

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents

arXiv 2502.20859 ↗First posted 28 Feb 2025cs.CLcited by 8

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

Abstract (arXiv)

Large language models (LLMs) excel in both closed tasks (including problem-solving, and code generation) and open tasks (including creative writing), yet existing explanations for their capabilities lack connections to real-world human intelligence. To fill this gap, this paper systematically investigates LLM intelligence through the lens of ``human simulation'', addressing three core questions: (1) textitHow do personality traits affect problem-solving in closed tasks? (2) textitHow do traits shape creativity in open tasks? (3) textitHow does single-agent performance influence multi-agent collaboration? By assigning Big Five personality traits to LLM agents and evaluating their performance in single- and multi-agent settings, we reveal that specific traits significantly influence reasoning accuracy (closed tasks) and creative output (open tasks). Furthermore, multi-agent systems exhibit collective intelligence distinct from individual capabilities, driven by distinguishing combinations of personalities.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 36 of its 75 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

36 of 75 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities16 Oct
  2. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 34

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  7. 2023Teaching Large Language Models to Self-Debugcited by 988
  8. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  9. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  10. 2022What learning algorithm is in-context learning? Investigations with linear modelscited by 684
  11. 2024A Survey on Large Language Models for Code Generationcited by 658
  12. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 523
22 more
  1. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  2. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 251
  3. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  4. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  5. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  6. 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoningcited by 156
  7. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  8. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  9. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  10. 2024LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Playcited by 66
  11. 2024Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inferencecited by 53
  12. 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learningcited by 29
  13. 2024QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correctioncited by 27
  14. 2024Exploring Safety-Utility Trade-Offs in Personalized Language Modelscited by 27
  15. 2024HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playingcited by 22
  16. 2024ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publicationscited by 20
  17. 2024Dynamic Planning for LLM-based Graphical User Interface Automationcited by 19
  18. 2024Evaluating Diversity in Automatic Poetry Generationcited by 17
  19. 2024Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspectivecited by 15
  20. 2024LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulationcited by 15
  21. 2024Evolving Agents: Interactive Simulation of Dynamic and Diverse Human Personalitiescited by 14
  22. 2023Exploring the Impact of Model Scaling on Parameter-Efficient Tuningcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2026PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systemscited by 4
  2. 2025Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialoguescited by 3
  3. 2026The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMscited by 1
  4. 2026When Does Personality Composition Matter for Multi-Agent LLM Teams?cited by 1
  5. 2025Wage Sentiment Indices Derived from Survey Comments via Large Language Modelscited by 0
  6. 2025Modeling Layered Consciousness with Multi-Agent Large Language Modelscited by 0
  7. 2026Multi-agent AI systems outperform human teams in creativitycited by 0
  8. 2026Agents with Feelings? Personality and Emotion in Multi-Agent Software Teamscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models
  2. 2026Experiences Build Characters: The Linguistic Origins and Functional Impact of LLM Personality
  3. 2026Structured Personality Control and Adaptation for LLM Agents
  4. 2025Mind the Gap: The Divergence Between Human and LLM-Generated Tasks
  5. 2025Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering
  6. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
  7. 2025Psychologically Enhanced AI Agents
  8. 2025Large Language Model Agent Personality and Response Appropriateness: Evaluation by Human Linguistic Experts, LLM-as-Judge, and Natural Language Processing Model