Metraipolis › archive › dc_6ef296722afd

From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers — arXiv:2609.21349

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21349
License (as archived)
CC0-1.0
Archived
2026-10-10T01:07:57.364Z
SHA-256 of the archived text
79e9289a269a43968ac3579b146284b73ddb1aa40c805d972775a0d0e4aaaea5
Stable URL of this page
https://metraipolis.com/documento/dc_6ef296722afd

How to cite

From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers — arXiv:2609.21349 — arXiv (en), https://arxiv.org/abs/2609.21349 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ef296722afd (Metraipolis archive dc_6ef296722afd, sha256 79e9289a269a43968ac3579b146284b73ddb1aa40c805d972775a0d0e4aaaea5)
BibTeX
@misc{dc6ef296722afd,
  title = {From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers — arXiv:2609.21349},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21349},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ef296722afd; sha256 79e9289a269a43968ac3579b146284b73ddb1aa40c805d972775a0d0e4aaaea5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21349. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existing in-context learning-based methods fail to capture how individuals react under different situations. In addition, LLM-based evaluation is difficult for obscure individuals. To address these challenges, we propose Situation--Internal state--Behavior Persona method to incorporate situation-dependent behavioral strategies. We further design an evaluation protocol that provides LLM evaluators with references about the impersonated individual. We evaluate our approach on a newly constructed dataset for the task of generating replies on social media. Experimental results show that our proposed method outperforms state-of-the-art ICL-based baselines, while our evaluation protocol achieves moderate correlation with human judgment. Besides, experiments on fictional-character benchmarks demonstrate that our proposed method is applicable beyond the social media setting. These findings suggest that incorporating behavioral information broadly improves the fidelity of role-playing for real individuals on social media or fictional characters.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.21349 — 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 2026-10-10T00:23:42.529Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).