# Do Personality-Tuned LLMs Make Better Social Agents?

arXiv: https://arxiv.org/abs/2609.21857 · HTML: https://mlsanity.com/paper/2609.21857/

## Key facts

- No citing papers in the map yet (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 21 of its 36 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [AgentSims: An Open-Source Sandbox for Large Language Model Evaluation](https://mlsanity.com/paper/2308.04026/) (2023)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities](https://mlsanity.com/paper/2405.06700/) (2024)
- [Population-Aligned Persona Generation for LLM-based Social Simulation](https://mlsanity.com/paper/2509.10127/) (2025)
- [Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models](https://mlsanity.com/paper/1907.06333/) (2019)
- [GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks](https://mlsanity.com/paper/2306.13679/) (2023)
- [From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation](https://mlsanity.com/paper/2507.19364/) (2025)
- [Negotiating Comfort: Simulating Personality-Driven LLM Agents in Shared Residential Social Networks](https://mlsanity.com/paper/2507.09657/) (2025)
- [The paradox of productivity during quarantine: an agent-based simulation](https://mlsanity.com/paper/2008.09461/) (2020)

## Abstract (arXiv)

LLMs are increasingly used in social simulations for socially interactive agents and robots, offering more flexibility than rule-based systems. However, even though they mimic human behaviour very well, there is a persistent alienness to them. This work investigates whether personality-aware fine-tuning can reduce this gap by improving the consistency and controllability of personality-conditioned dialogue generation compared with instruction prompting alone. We fine-tune two small open-weight LLMs, Qwen2.5-7B-Instruct and Ministral-8B-Instruct, using a corpus that combines personality-labelled social media posts and dialogues to create a personality-based dialogue engine for social simulation. The resulting models are evaluated across multiple social interaction scenarios using three independent LLM judges, which assess personality fidelity and provide evidence-based behavioral interpretations. We additionally quantify inter-rater agreement and lexical characteristics of the generated dialogue. Results indicate that fine-tuned models are not better at role-playing different personalities than their respective baseline models. However, low inter-rater agreement limits the confidence with which these results can be interpreted. Concerning the quality of generated texts, fine-tuned models are mostly comparable to the baselines, with fine-tuning improving the linguistic diversity of the Qwen models. While the results appear generally usable and the baseline models offer the best overall performance, future studies should place greater emphasis on the quality and domain alignment of training data for accurate personality role-playing.