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

• URL: http://arxiv.org/abs/2508.02016v2
• Date: Fri, 26 Sep 2025 01:28:35 GMT
• Title: Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations
• Authors: Jeiyoon Park, Yongshin Han, Minseop Kim, Kisu Yang,
• Abstract summary: We propose Amadeus, a training-free framework for role-playing agents (RPAs)<n>A Amadeus framework can significantly enhance persona consistency even when responding to questions that lie beyond a character's knowledge.
• Score: 1.1740676332544449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• What Makes You Unique? Attribute Prompt Composition for Object Re-Identification [70.67907354506278]
  Object Re-IDentification aims to recognize individuals across non-overlapping camera views.<n>Single-domain models tend to overfit to domain-specific features, whereas cross-domain models often rely on diverse normalization strategies.<n>We propose an Attribute Prompt Composition framework, which exploits textual semantics to jointly enhance discrimination and generalization.
  arXiv  Detail & Related papers  (2025-09-23T07:03:08Z)
• RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing [111.06936588273868]
  RMTBench is a comprehensive textbfuser-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.<n>Our benchmark constructs dialogues based on explicit user motivations rather than character descriptions, ensuring alignment with practical user applications.<n>By shifting focus from character background to user intention fulfillment, RMTBench bridges the gap between academic evaluation and practical deployment requirements.
  arXiv  Detail & Related papers  (2025-07-27T16:49:47Z)
• A Modular Unsupervised Framework for Attribute Recognition from Unstructured Text [0.0]
  POSID is a framework for extracting structured attribute-based properties from unstructured text.<n>We demonstrate its effectiveness on a missing person use case using the InciText dataset.
  arXiv  Detail & Related papers  (2025-07-05T08:22:52Z)
• RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval [6.636092764694501]
  RoleRAG is a retrieval-based framework that integrates efficient entity disambiguation for knowledge indexing with a boundary-aware retriever for extracting contextually appropriate information from a structured knowledge graph.<n> Experiments on role-playing benchmarks show that RoleRAG's calibrated retrieval helps both general-purpose and role-specific LLMs better align with character knowledge and reduce hallucinated responses.
  arXiv  Detail & Related papers  (2025-05-24T06:11:17Z)
• Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation [52.3707788779464]
  We introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD)<n>ARC-JSD enables efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling.<n> Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements.
  arXiv  Detail & Related papers  (2025-05-22T09:04:03Z)
• LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification [63.07563443280147]
  We propose a novel framework named LATex for AG-ReID.<n>It adopts prompt-tuning strategies to leverage attribute-based text knowledge.<n>Our framework can fully leverage attribute-based text knowledge to improve the AG-ReID.
  arXiv  Detail & Related papers  (2025-03-31T04:47:05Z)
• Improving RAG for Personalization with Author Features and Contrastive Examples [2.6968321526169503]
  Personalization with retrieval-augmented generation (RAG) often fails to capture fine-grained features of authors.<n>We introduce Contrastive Examples: documents from other authors are retrieved to help LLM identify what makes an author's style unique in comparison to others.<n>Our results show the value of fine-grained features for better personalization, while opening a new research dimension for including contrastive examples as a complement with RAG.
  arXiv  Detail & Related papers  (2025-03-24T01:41:22Z)
• CoSER: Coordinating LLM-Based Persona Simulation of Established Roles [62.886267684392635]
  CoSER dataset covers 17,966 characters from 771 renowned books.<n>We develop CoSER 8B and CoSER 70B, i.e., advanced open role-playing LLMs built on LLaMA-3.1 models.
  arXiv  Detail & Related papers  (2025-02-13T08:55:24Z)
• CharacterBench: Benchmarking Character Customization of Large Language Models [80.29164862682063]
  We propose CharacterBench, the largest bilingual generative benchmark, with 22,859 human-annotated samples covering 3,956 characters.<n>We define 11 dimensions of 6 aspects, classified as sparse and dense dimensions based on whether character features evaluated by specific dimensions manifest in each response.<n>We also develop CharacterJudge model for cost-effective and stable evaluations.
  arXiv  Detail & Related papers  (2024-12-16T15:55:34Z)
• CHATTER: A Character Attribution Dataset for Narrative Understanding [31.540540919042154]
  We validate a subset of CHATTER, called CHATTEREVAL, using human annotations to serve as a benchmark to evaluate the character attribution task in movie scripts.<n>evaldataset also assesses narrative understanding and the long-context modeling capacity of language models.
  arXiv  Detail & Related papers  (2024-11-07T22:37:30Z)
• BookWorm: A Dataset for Character Description and Analysis [59.186325346763184]
  We define two tasks: character description, which generates a brief factual profile, and character analysis, which offers an in-depth interpretation. We introduce the BookWorm dataset, pairing books from the Gutenberg Project with human-written descriptions and analyses. Our findings show that retrieval-based approaches outperform hierarchical ones in both tasks.
  arXiv  Detail & Related papers  (2024-10-14T10:55:58Z)
• GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation [3.2027710059627545]
  We introduce Graphical Eigen Memories For Retrieval Augmented Generation (GEM-RAG) GEM-RAG works by tagging each chunk of text in a given text corpus with LLM generated utility'' questions. We evaluate GEM-RAG, using both UnifiedQA and GPT-3.5 Turbo as the LLMs, with SBERT, and OpenAI's text encoders on two standard QA tasks.
  arXiv  Detail & Related papers  (2024-09-23T21:42:47Z)
• Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation [65.16137964758612]
  We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text.
  arXiv  Detail & Related papers  (2024-05-31T20:15:10Z)
• CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models [49.16989035566899]
  Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios.
  arXiv  Detail & Related papers  (2024-01-30T14:25:32Z)
• Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification [18.01407937934588]
  We present a new framework called Multi-Prompts ReID (MP-ReID) based on prompt learning and language models. MP-ReID learns to hallucinate diverse, informative, and promptable sentences for describing the query images. Explicit prompts are obtained by ensembling generation models, such as ChatGPT and VQA models.
  arXiv  Detail & Related papers  (2023-12-28T03:00:19Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark [24.366997699462075]
  We introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning framework.
  arXiv  Detail & Related papers  (2023-06-05T14:06:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.