Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915774814224384 |
|---|---|
| author | Park, Jeiyoon Han, Yongshin Kim, Minseop Yang, Kisu |
| author_facet | Park, Jeiyoon Han, Yongshin Kim, Minseop Yang, Kisu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02016 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations Park, Jeiyoon Han, Yongshin Kim, Minseop Yang, Kisu Artificial Intelligence 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. |
| title | Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.02016 |