# Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts

arXiv: https://arxiv.org/abs/2602.03545 · HTML: https://mlsanity.com/paper/2602.03545/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 30 of 36)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings](https://mlsanity.com/paper/2304.01433/) (2023)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [Aligning Large Language Models through Synthetic Feedback](https://mlsanity.com/paper/2305.13735/) (2023)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [Quality-Diversity through AI Feedback](https://mlsanity.com/paper/2310.13032/) (2023)
- [Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis](https://mlsanity.com/paper/2405.07248/) (2024)
- [A theory of appropriateness with applications to generative artificial intelligence](https://mlsanity.com/paper/2412.19010/) (2024)
- [Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires](https://mlsanity.com/paper/2502.05248/) (2025)
- [DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas](https://mlsanity.com/paper/2511.07338/) (2025)
- [Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models](https://mlsanity.com/paper/2506.07121/) (2025)
- [PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming](https://mlsanity.com/paper/2509.03728/) (2025)
- [A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas](https://mlsanity.com/paper/2505.07850/) (2025)

## Built on by (most cited first, 6 of 6)

- [A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms](https://mlsanity.com/paper/2609.04170/) (2026)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [Discovering Novel LLM Experts via Task-Capability Coevolution](https://mlsanity.com/paper/2604.14969/) (2026)
- [Can AI Agents Simulate A/B Test Outcomes? A Validation Framework for Agentic Experimentation](https://mlsanity.com/paper/2608.02345/) (2026)
- [Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs](https://mlsanity.com/paper/2609.30492/) (2026)
- [Benchmarking Psychological Dynamics in Generative Agents](https://mlsanity.com/paper/2610.04246/) (2026)

## Abstract (arXiv)

Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive or infeasible, particularly for novel technologies or hypothetical future scenarios. Recent work in Generative Agent-Based Modeling has shown that large language models can simulate human-like synthetic personas with high fidelity, accurately reproducing the beliefs and behaviors of specific individuals. However, most approaches require detailed data about target populations and often prioritize density matching (replicating what is most probable) rather than support coverage (spanning what is possible), leaving long-tail behaviors underexplored. We introduce Persona Generators, functions that can produce diverse synthetic populations tailored to arbitrary contexts. We apply an iterative improvement loop based on AlphaEvolve, using large language models as mutation operators to refine our Persona Generator code over hundreds of iterations. The optimization process produces lightweight Persona Generators that can automatically expand small descriptions into populations of diverse synthetic personas that maximize coverage of opinions and preferences along relevant diversity axes. We demonstrate that evolved generators substantially outperform existing baselines across six diversity metrics on held-out contexts, producing populations that span rare trait combinations difficult to achieve in standard LLM outputs.