mlsanityData to 7 Oct 2026

LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models

arXiv 2402.02896 ↗First posted 5 Feb 2024cs.CL cs.AI cs.CYcited by 33

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

Abstract (arXiv)

While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an endeavour is important to ensure that agents remain consistent to their assigned traits yet are able to engage in open, naturalistic dialogues. In our experiments, we condition GPT-3.5 on personality profiles through prompting and create a two-group population of LLM agents using a simple variability-inducing sampling algorithm. We then administer personality tests and submit the agents to a collaborative writing task, finding that different profiles exhibit different degrees of personality consistency and linguistic alignment to their conversational partners. Our study seeks to lay the groundwork for better understanding of dialogue-based interaction between LLMs and highlights the need for new approaches to crafting robust, more human-like LLM personas for interactive environments.

Key facts. Cited by 33 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 13 of its 31 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

13 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023On the Effectiveness of Creating Conversational Agent Personalities Through Prompting17 Oct
  2. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 11

  1. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  2. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  3. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  4. 2016A Persona-Based Neural Conversation Modelcited by 221
  5. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 181
  6. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
  7. 2020Analysing Lexical Semantic Change with Contextualised Word Representationscited by 92
  8. 2023What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variabilitycited by 51
  9. 2022Identifying and Manipulating the Personality Traits of Language Modelscited by 40
  10. 2019Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrastcited by 12
  11. 2018Semantic Variation in Online Communities of Practicecited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 15; 2026: 13.

33 papers.

Sort:

By area:

  1. 2024BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Datacited by 49
  2. 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learningcited by 35
  3. 2024Evaluating Large Language Models with Psychometricscited by 22
  4. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  5. 2025Unmasking Conversational Bias in AI Multiagent Systemscited by 16
  6. 2024Trust-Oriented Adaptive Guardrails for Large Language Modelscited by 8
  7. 2024The influence of persona and conversational task on social interactions with a LLM-controlled embodied conversational agentcited by 7
  8. 2025FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheetscited by 7
  9. 2024Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptorscited by 6
  10. 2026Attractor States Emerge in Multi-Turn LLM Conversationscited by 6
  11. 2025AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefscited by 4
  12. 2025Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialoguescited by 3
21 more
  1. 2025Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMscited by 3
  2. 2025Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?cited by 3
  3. 2026AI-exhibited Personality Traits Can Shape Human Self-concept through Conversationscited by 3
  4. 2026Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)cited by 3
  5. 2025Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Realitycited by 2
  6. 2025Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AIcited by 2
  7. 2026Dynamic Personality Adaptation in Large Language Models via State Machinescited by 2
  8. 2026Enhancing Safety of Large Language Models via Embedding Space Separationcited by 2
  9. 2025LLM Agent-Based Simulation of Student Activities and Mental Health Using Smartphone Sensing Datacited by 1
  10. 2025The Adaptation Paradox: Agency vs. Mimicry in Companion Chatbotscited by 1
  11. 2025TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Educationcited by 1
  12. 2026IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variationcited by 1
  13. 2025LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferencescited by 0
  14. 2025Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMscited by 0
  15. 2026Never say never: Exploring the effects of available knowledge on agent persuasiveness in controlled physiotherapy motivation dialoguescited by 0
  16. 2026InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspectioncited by 0
  17. 2026An Interactive Paradigm for Deep Researchcited by 0
  18. 2026Synthetic Counteradaptation: A Principle of Human-AI Co-evolutioncited by 0
  19. 2026The Story Shapes the Agent: Narrative Priors in LLM Behaviorcited by 0
  20. 2026When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMscited by 0
  21. 2026When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debatecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Can LLM Agents Maintain a Persona in Discourse?
  2. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
  3. 2026Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
  4. 2024Examining Identity Drift in Conversations of LLM Agents
  5. 2026Structured Personality Control and Adaptation for LLM Agents
  6. 2025Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
  7. 2026Do Personality-Tuned LLMs Make Better Social Agents?
  8. 2026Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis