🤖 AI Summary
This study addresses a key challenge in developing socially trustworthy artificial intelligence: constructing human-like agents that exhibit both stable personality traits and adaptive behavior across diverse social contexts. The authors propose a novel architecture integrating the Big Five personality model with Bourdieu’s theory of cognitive–social co-construction, comprising an Individual Structure (IS) and a Multi-Scenario Contextual (MSC) framework. By leveraging structured prompts, the approach guides small language models to generate responses that are both personality-consistent and contextually appropriate. The method innovatively couples psychological personality modeling with sociological contextual structures through structured agent profiles, role–relationship–norm-based scenario modeling, and fixed prompt binding. Empirical results demonstrate significant improvements over non-fine-tuned large-model baselines in personality consistency, contextual adaptability, and stylistic alignment, while ablation studies confirm the essential contributions of both IS and MSC components.
📝 Abstract
Human-like agents require modeling how dispositions interact with social structure. We present PsyAgent, which couples a Big Five trait prior with Bourdieu's cognitive-social co-structure. PsyAgent comprises: (i) Individual Structure (IS), a machine-usable profile encoding traits and facets, cognitive style, values, cultural and educational capital, and salient life episodes; and (ii) Multi-Scenario Contexting (MSC), role-relationship-norm frames spanning eight arenas (work, family, friendship, strangers and civic life, solitude and self-regulation, romance, learning, and public expression). At inference, fixed structured prompts bind the active scenario to the agent profile, yielding behavior that is stable yet context-sensitive. We instantiate IS and MSC to synthesize supervision (role-play dialogues, decision probes, feedback trajectories) and then fine-tune a small LLM. The resulting model produces consistent, identifiable persona-aligned behaviors for specified Big Five configurations and matches or exceeds several larger untuned LLMs and other untuned baselines on our metrics: persona consistency, contextual appropriateness, style matching, trait identifiability, and long-horizon stability. Ablations show IS chiefly improves trait fidelity and stylistic stability, while MSC drives norm awareness and decision fit; both are necessary for cross-scenario performance. PsyAgent offers a precise, data-efficient architecture for personality-grounded agents.