arXiv：cs.AI· Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying Chen·· 6 小时前AI 评分32
MASC：面向心理咨询中一致来访者角色扮演的多智能体自校准框架与潜在构念对齐
MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
AI 导读
研究者提出 MASC，一个结合构念引导生成、协同精炼、一致性验证与基于记忆修正的多智能体自校准框架，用于心理咨询中一致的来访者角色扮演。同时发布 CRPC-Bench 基准，涵盖会话级画像与 Big-Five 人格特质，以及轮次级心理状态、沟通行为与情绪表达，含 38 个动机式访谈来访者画像。实验显示 MASC 在画像、人格、接受度与轮次级一致性上优于现有方法，异构配置整体表现最佳。
正文
Abstract:Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit persona drift, unrealistic cooperativeness, or inconsistent psychological states, communicative actions, and emotions. Existing evaluations also lack a unified testbed for both stable client characteristics and evolving psychological dynamics. We propose MASC, a Multi-Agent Self-Calibration framework with latent construct alignment for consistent client role-playing in psychological counseling. MASC combines construct-guided generation, collaborative refinement, consistency verification, and memory-based revision in a closed calibration loop that detects and corrects inconsistencies as dialogue unfolds. We further introduce CRPC-Bench, a benchmark covering session-level profile information and Big-Five personality traits, as well as turn-level psychological state, communicative action, and emotion expression. CRPC-Bench contains 38 motivational interviewing client profiles augmented with personality and emotion annotations. Experiments show that MASC outperforms existing methods across profile, personality, receptivity, and turn-level consistency, with the heterogeneous configuration achieving the strongest overall performance. MASC and CRPC-Bench provide a unified foundation for developing and evaluating psychologically coherent client simulations for AI-assisted counseling research and training.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08250 [cs.AI] |
| (or arXiv:2610.08250v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08250 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiaxing Zheng [view email]
[v1]
Tue, 6 Oct 2026 12:31:05 UTC (458 KB)
来源：arXiv：cs.AI · arxiv.org