mlsanityData to 14 Oct 2026

Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust

arXiv 2507.02197 ↗First posted 2 Jul 2025cs.AIcited by 6

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

Abstract (arXiv)

As LLMs are increasingly studied as role-playing agents to generate synthetic data for human behavioral research, ensuring that their outputs remain coherent with their assigned roles has become a critical concern. In this paper, we investigate how consistently LLM-based role-playing agents' stated beliefs about the behavior of the people they are asked to role-play ("what they say") correspond to their actual behavior during role-play ("how they act"). Specifically, we establish an evaluation framework to rigorously measure how well beliefs obtained by prompting the model can predict simulation outcomes in advance. Using an augmented version of the GenAgents persona bank and the Trust Game (a standard economic game used to quantify players' trust and reciprocity), we introduce a belief-behavior consistency metric to systematically investigate how it is affected by factors such as: (1) the types of beliefs we elicit from LLMs, like expected outcomes of simulations versus task-relevant attributes of individual characters LLMs are asked to simulate; (2) when and how we present LLMs with relevant information about Trust Game; and (3) how far into the future we ask the model to forecast its actions. We also explore how feasible it is to impose a researcher's own theoretical priors in the event that the originally elicited beliefs are misaligned with research objectives. Our results reveal systematic inconsistencies between LLMs' stated (or imposed) beliefs and the outcomes of their role-playing simulation, at both an individual- and population-level. Specifically, we find that, even when models appear to encode plausible beliefs, they may fail to apply them in a consistent way. These findings highlight the need to identify how and when LLMs' stated beliefs align with their simulated behavior, allowing researchers to use LLM-based agents appropriately in behavioral studies.

Key facts. Cited by 6 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 29 of its 42 references that are in the map. First posted on arXiv 2 Jul 2025.

Builds on

29 of 42 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy12 Mar
  2. 2025Can LLM Agents Maintain a Persona in Discourse?17 Feb
  3. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals15 Nov
  4. 2024On the limits of agency in agent-based models14 Sep
  5. 2023LARP: Language-Agent Role Play for Open-World Games24 Dec
  6. 2023Character-LLM: A Trainable Agent for Role-Playing16 Oct
  7. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 22

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  5. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  7. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 244
  8. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  9. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 98
  10. 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 73
  11. 2025Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?cited by 51
  12. 2024The illusion of artificial inclusioncited by 34
10 more
  1. 2025LLM-based Human Simulations Have Not Yet Been Reliablecited by 30
  2. 2024Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?cited by 26
  3. 2024Controllable Context Sensitivity and the Knob Behind Itcited by 23
  4. 2025The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucinationcited by 23
  5. 2024Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environmentscited by 17
  6. 2025User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluationcited by 17
  7. 2024When Context Leads but Parametric Memory Follows in Large Language Modelscited by 11
  8. 2024Characteristic AI Agents via Large Language Modelscited by 5
  9. 2024Focus On This, Not That! Steering LLMs with Adaptive Feature Specificationcited by 5
  10. 2024Uncovering Name-Based Biases in Large Language Models Through Simulated Trust Gamecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narrativescited by 2
  2. 2026MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulationscited by 1
  3. 2026Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflictcited by 0
  4. 2026TUX: Measuring Human--AI Tacit Understandingcited by 0
  5. 2026Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systemscited by 0
  6. 2026ANIMASK: What the Model Contributes to Role Play in Simulated Story Worldscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Can Large Language Model Agents Simulate Human Trust Behavior?
  2. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks
  3. 2025When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma
  4. 2025Social preferences with unstable interactive reasoning: Large language models in economic trust games
  5. 2025A closer look at how large language models trust humans: patterns and biases
  6. 2025Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents
  7. 2026Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase Outcomes
  8. 2026HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing