Metraipolis › archive › dc_316fc3a28049

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations — arXiv:2609.22255

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22255
License (as archived)
CC0-1.0
Archived
2026-10-09T06:49:27.050Z
SHA-256 of the archived text
086ba4fe3a9e289669c7faeccd763d65772de02ce292038e3155715d71ba0550
Stable URL of this page
https://metraipolis.com/documento/dc_316fc3a28049

How to cite

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations — arXiv:2609.22255 — arXiv (en), https://arxiv.org/abs/2609.22255 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_316fc3a28049 (Metraipolis archive dc_316fc3a28049, sha256 086ba4fe3a9e289669c7faeccd763d65772de02ce292038e3155715d71ba0550)
BibTeX
@misc{dc316fc3a28049,
  title = {Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations — arXiv:2609.22255},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22255},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_316fc3a28049; sha256 086ba4fe3a9e289669c7faeccd763d65772de02ce292038e3155715d71ba0550},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22255. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes personas into hierarchical levels of observable expression, latent beliefs, and core motivational drives, for constructing highly convincing role-playing agents. Governed by the principles of scripted determinism and bounded agency, the architecture restricts the model to a reactive engine guided by a structured internal script. We further propose a reference-free evaluation framework that benchmarks dialogue naturalness against empirical human distributions using established psychological clinical instruments and adversarial stress-tests. Empirical evaluation reveals that while LLMs achieve high pragmatic fluency, they exhibit systematic limitations in emotional expression and joint attention. In addition, we present a case study of two Deep Personas and evaluate them using the proposed framework, demonstrating that structured personas can produce interactions that more closely align with human conversational behavior.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.22255 — 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 2026-10-09T06:48:44.919Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).