用心理模型构建能稳定适应情境的人类代理，兼顾性格一致与社会规范。
PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction
- 以五大性格特质为基础，结合角色-关系-规范框架生成行为
- 在长时对话中保持性格一致性，优于多个大模型基线
- 适合需要个性化、符合社会规范的智能体应用
人类式智能体需在保持性格稳定性的同时适应不同角色、关系与规范。本文提出PsyAgent，一种以框架优先的系统，通过将五大性格特质先验与显式的社会结构条件耦合，实现性格与情境的交互。PsyAgent包含两部分：(i) 个体结构（IS），即机器可读的性格化个体档案；(ii) 多场景情境库（MSC），涵盖八个日常场景的角色-关系-规范组合。推理时，固定结构提示将当前的MSC框架与IS档案结合，引导出既稳定又情境敏感的行为。为验证学习能力，我们使用IS与MSC合成监督信号，对紧凑模型进行参数高效微调（SFT及可选DPO）。在控制性心理测量评估协议（百分位空间）下，PsyAgent显著提升性格忠实度与长时行为稳定性，且在匹配解码与评分条件下，性能媲美多个更大规模通用指令微调基线。我们进一步通过外部基准和小型盲测人类研究进行三角验证。总体而言，PsyAgent提供了一种精确且数据高效的个性驱动、规范感知智能体构建方法。
原文摘要 · Abstract (English)
Human-like agents must express stable dispositions while adapting to roles, relationships, and norms. We present PsyAgent, a schema-first framework that operationalizes the trait-context interface by coupling a Big Five trait prior with explicit social-structural conditioning. PsyAgent comprises (i) Individual Structure (IS), a machine-usable trait-grounded profile, and (ii) Multi-Scenario Contexting (MSC), a curated library of role-relationship-norm frames spanning eight everyday arenas. At inference, fixed structured prompts couple the active MSC frame with the IS profile, encouraging behavior that is stable yet context-sensitive. To demonstrate learnability beyond prompt engineering, we use IS and MSC to synthesize supervision and fine-tune compact backbones with PEFT (SFT and optional DPO). Under a controlled psychometric-style evaluation protocol in percentile space, PsyAgent improves trait-faithfulness and long-horizon stability, and is competitive with several larger general-purpose instruction-tuned baselines under matched decoding and scoring controls. We further triangulate the automatic protocol with external benchmarks and a small blinded human study. Overall, PsyAgent provides a precise and data-efficient approach to personality-grounded, norm-aware agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。