arXiv：cs.AI· Yuting Yan, Shihao Xu, Junhao Yu, Mingcong Zuo, Lu Chen, Nan Xiang, Haiyang Geng, Dongjie Tao, Minghao Wang·· 5 小时前AI 评分42
PsyEvo：可在测试时自我进化的个性化心理咨询智能体
PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time
AI 导读
PsyEvo 是一个基于 LLM 的心理咨询框架，通过 Hierarchical Bayesian Skill Policy、Inter-session Listwise Preference Optimization 和 State-conditioned Ordinal Credit Assignment 三个组件，在测试时实现针对来访者的个性化与响应策略改进。
正文
Abstract:Mental health disorders affect a substantial proportion of the global population, yet a persistent shortage of trained practitioners leaves the majority without adequate care. Large language model (LLM)-based counselors present a promising direction for delivering scalable conversational psychological support. Offline model training alone leaves limited room to adapt to individual clients or to learn from ongoing therapeutic interaction at test time. We introduce PsyEvo, an LLM-based counseling framework that enables both client-specific personalization and response-policy improvement at test time through three components: Hierarchical Bayesian Skill Policy (HBSP) personalizes what intervention to apply by maintaining a per-client skill posterior updated from session feedback; Inter-session Listwise Preference Optimization (LiPO) improves how the selected skill is expressed by updating a shared response adapter from cross-client preference evidence; and State-conditioned Ordinal Credit Assignment (SOCA) supplies candidate preferences and trajectory credit to the two components through consistency-checked comparisons and ordinal projection. In simulated-client evaluation with shared online cohort adaptation, PsyEvo obtains 7.684 Overall on PsychEval and exceeds every component variant in each of three matched runs. Removing individual components lowers mean overall score by 0.138--0.171 under the shared configuration, supporting conditional contributions within the complete scaffold. Our code is available at this https URL
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02885 [cs.AI] |
| (or arXiv:2610.02885v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02885 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shihao Xu [view email]
[v1]
Fri, 2 Oct 2026 06:23:23 UTC (1,184 KB)
来源：arXiv：cs.AI · arxiv.org