dorsal/arxiv
View SchemaPsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction
| Authors | Zibin Meng, Kani Chen |
|---|---|
| Categories | |
| ArXiv ID | 2601.06158vv1 |
| URL | https://arxiv.org/abs/2601.06158 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
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.
{
"annotation_id": "27b07096-166c-49b5-a5f0-867a6db31fbf",
"date_created": "2026-02-17T05:53:05.103000Z",
"date_modified": "2026-02-17T05:53:05.103000Z",
"file_hash": "15ea01825ca621b9a49da70cc0026636ec4c1ec286320e6675bc210aa842fed5",
"private": false,
"record": {
"abstract": "Human-like agents require modeling how dispositions interact with social structure. We present PsyAgent, which couples a Big Five trait prior with Bourdieu\u0027s 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.",
"arxiv_id": "2601.06158",
"authors": [
"Zibin Meng",
"Kani Chen"
],
"categories": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction",
"url": "https://arxiv.org/abs/2601.06158",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "ac98e638-467e-4aa6-82ba-ffe50e06b686",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}