{"ID":2886658,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02016","arxiv_id":"2508.02016","title":"Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations","abstract":"Building role-playing agents (RPAs) that faithfully emulate specific characters remains challenging because collecting character-specific utterances and continually updating model parameters are resource-intensive, making retrieval-augmented generation (RAG) a practical necessity. However, despite the importance of RAG, there has been little research on RAG-based RPAs. For example, we empirically find that when a persona lacks knowledge relevant to a given query, RAG-based RPAs are prone to hallucination, making it challenging to generate accurate responses. In this paper, we propose Amadeus, a training-free framework that can significantly enhance persona consistency even when responding to questions that lie beyond a character's knowledge. In addition, to underpin the development and rigorous evaluation of RAG-based RPAs, we manually construct CharacterRAG, a role-playing dataset that consists of persona documents for 15 distinct fictional characters totaling 976K written characters, and 450 question-answer pairs. We find that our proposed method effectively models not only the knowledge possessed by characters, but also various attributes such as personality.","short_abstract":"Building role-playing agents (RPAs) that faithfully emulate specific characters remains challenging because collecting character-specific utterances and continually updating model parameters are resource-intensive, making retrieval-augmented generation (RAG) a practical necessity. However, despite the importance of RAG...","url_abs":"https://arxiv.org/abs/2508.02016","url_pdf":"https://arxiv.org/pdf/2508.02016v4","authors":"[\"Jeiyoon Park\",\"Yongshin Han\",\"Minseop Kim\",\"Kisu Yang\"]","published":"2025-08-04T03:27:05Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\"]","has_code":false}