PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction

Researchers introduce PsyAgent, a new AI framework that creates human-like agents by combining personality modeling based on Big Five traits with contextual social awareness. The system uses structured prompts and fine-tuning to produce AI agents that maintain stable personality traits while adapting appropriately to different social situations and roles.

• →PsyAgent combines Big Five personality traits with social context modeling to create more human-like AI agents.
• →The framework includes Individual Structure (trait profiles) and Multi-Scenario Contexting (social situation library) components.
• →The system demonstrates improved trait-faithfulness and stability compared to larger general-purpose AI models.
• →PsyAgent can be fine-tuned using Parameter Efficient Fine-Tuning (PEFT) methods for better performance.
• →The approach offers a data-efficient method for creating personality-grounded, norm-aware AI agents.