# Persona Alchemy: Designing, Evaluating, and Implementing Psychologically-Grounded LLM Agents for Diverse Stakeholder Representation

arXiv: https://arxiv.org/abs/2505.18351 · HTML: https://mlsanity.com/paper/2505.18351/

## Key facts

- Cited by 2 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 18 of its 58 references that are in the map.
- First posted on arXiv 23 May 2025.

## 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, 18 of 18)

- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://mlsanity.com/paper/2212.10465/) (2022)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [The illusion of artificial inclusion](https://mlsanity.com/paper/2401.08572/) (2024)
- [Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas](https://mlsanity.com/paper/2406.14462/) (2024)
- [The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?](https://mlsanity.com/paper/2305.07970/) (2023)
- [CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models](https://mlsanity.com/paper/2402.15265/) (2024)
- [Eliciting Personality Traits in Large Language Models](https://mlsanity.com/paper/2402.08341/) (2024)
- ["In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning](https://mlsanity.com/paper/2403.03102/) (2024)
- [Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge](https://mlsanity.com/paper/2407.03958/) (2024)
- [MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space](https://mlsanity.com/paper/2407.02345/) (2024)
- [Personality Differences Drive Conversational Dynamics: A High-Dimensional NLP Approach](https://mlsanity.com/paper/2410.11043/) (2024)

## Built on by (most cited first, 2 of 2)

- [Using AI for User Representation: An Analysis of 83 Persona Prompts](https://mlsanity.com/paper/2508.13047/) (2025)
- [Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies](https://mlsanity.com/paper/2603.23406/) (2026)

## Abstract (arXiv)

Despite advances in designing personas for Large Language Models (LLM), challenges remain in aligning them with human cognitive processes and representing diverse stakeholder perspectives. We introduce a Social Cognitive Theory (SCT) agent design framework for designing, evaluating, and implementing psychologically grounded LLMs with consistent behavior. Our framework operationalizes SCT through four personal factors (cognitive, motivational, biological, and affective) for designing, six quantifiable constructs for evaluating, and a graph database-backed architecture for implementing stakeholder personas. Experiments tested agents' responses to contradicting information of varying reliability. In the highly polarized renewable energy transition discourse, we design five diverse agents with distinct ideologies, roles, and stakes to examine stakeholder representation. The evaluation of these agents in contradictory scenarios occurs through comprehensive processes that implement the SCT. Results show consistent response patterns (R2 range: 0.58-0.61) and systematic temporal development of SCT construct effects. Principal component analysis identifies two dimensions explaining 73% of variance, validating the theoretical structure. Our framework offers improved explainability and reproducibility compared to black-box approaches. This work contributes to ongoing efforts to improve diverse stakeholder representation while maintaining psychological consistency in LLM personas.