Metraipolis › archive › dc_dda7ea925033

PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time — arXiv:2610.02885

Source
arXiv
Original
https://arxiv.org/abs/2610.02885
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:20.037Z
SHA-256 of the archived text
e18c680462f55b492615859f0334716fcc43b16f0a12854877ace57e16c2ae3c
Stable URL of this page
https://metraipolis.com/documento/dc_dda7ea925033

How to cite

PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time — arXiv:2610.02885 — arXiv, https://arxiv.org/abs/2610.02885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dda7ea925033 (Metraipolis archive dc_dda7ea925033, sha256 e18c680462f55b492615859f0334716fcc43b16f0a12854877ace57e16c2ae3c)
BibTeX
@misc{dcdda7ea925033,
  title = {PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time — arXiv:2610.02885},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02885},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dda7ea925033; sha256 e18c680462f55b492615859f0334716fcc43b16f0a12854877ace57e16c2ae3c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02885 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.646Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).