FictionRAG: A Stateful Metacognitive Framework for High-Fidelity Long-Narrative Role-Playing

Maintaining high-fidelity character personas and tracking trusted narrative facts remain significant challenges for LLM-based role-playing systems, particularly in long-context scenarios. Traditional Retrieval-Augmented Generation (RAG) approaches, which typically rely on static, stateless retrieval...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yifei Deng, Yudong Zhang, Jingpu Yang, Miao Fang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-05-01
coleção:	Algorithms
Assuntos:	role-playing large language models retrieval-augmented generation stateful reasoning dynamic memory persona consistency
Acesso em linha:	https://www.mdpi.com/1999-4893/19/5/383
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!