Metraipolis › archive › dc_3bef4c333fc0
SCorPion: A Strategic, Controllable and Personified Conversational Companion — arXiv:2611.10906
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10906
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:31.281Z
- SHA-256 of the archived text
fac15b3fe3d9b26d182ced03e8d218278e4043684bde42e6077fb7e1d2b1050a- Stable URL of this page
https://metraipolis.com/documento/dc_3bef4c333fc0
How to cite
SCorPion: A Strategic, Controllable and Personified Conversational Companion — arXiv:2611.10906 — arXiv (en), https://arxiv.org/abs/2611.10906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3bef4c333fc0 (Metraipolis archive dc_3bef4c333fc0, sha256 fac15b3fe3d9b26d182ced03e8d218278e4043684bde42e6077fb7e1d2b1050a)
BibTeX
@misc{dc3bef4c333fc0,
title = {SCorPion: A Strategic, Controllable and Personified Conversational Companion — arXiv:2611.10906},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10906},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3bef4c333fc0; sha256 fac15b3fe3d9b26d182ced03e8d218278e4043684bde42e6077fb7e1d2b1050a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fixed prompt-based language models face challenges in open-domain conversations, where versatile topics require different expert advice or demonstrations to maximize their universal performance. Motivated by the dynamic prompt studies in language generation, we extract different chatting strategies from varied forms of text corpus, which steer the language model to different styles based on human principles. We design and deploy a conversational companion called SCorPion, which uses GraphRAG to extract and summarize the knowledge graph globally, yield community-summarized strategies, and produce query-focused optimal strategies. SCorPion has strategic thinking, yields personified and stylized responses, and can be controlled by explicit factors. Code and further results can be found in this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.10906 — 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 2026-11-10T18:37:52.429Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).