AIAug 4, 2025

Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations

arXiv:2508.02016v24 citationsh-index: 3
Originality Incremental advance
AI Analysis

This addresses the challenge of maintaining consistent role-playing agents for applications like gaming or interactive storytelling, though it is incremental as it builds on existing RAG methods.

The paper tackles the problem of hallucination in retrieval-augmented generation (RAG) based role-playing agents when queries fall outside a character's knowledge, proposing Amadeus, a training-free framework that enhances persona consistency, and introduces CharacterRAG, a dataset with 15 characters and 450 question-answer pairs, showing effective modeling of character knowledge and attributes.

Recent advances in large language models (LLMs) have catalyzed research on role-playing agents (RPAs). However, the process of collecting character-specific utterances and continually updating model parameters to track rapidly changing persona attributes is resource-intensive. Although retrieval-augmented generation (RAG) can alleviate this problem, if a persona does not contain 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. Amadeus is composed of Adaptive Context-aware Text Splitter (ACTS), Guided Selection (GS), and Attribute Extractor (AE). To facilitate effective RAG-based role-playing, ACTS partitions each character's persona into optimally sized, overlapping chunks and augments this representation with hierarchical contextual information. AE identifies a character's general attributes from the chunks retrieved by GS and uses these attributes as a final context to maintain robust persona consistency even when answering out-of-knowledge questions. 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes