mlsanityData to 7 Oct 2026

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

arXiv 2508.02016 ↗First posted 4 Aug 2025cs.AIcited by 4

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 28 of its 46 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

28 of 46 references.

References · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  7. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  8. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  9. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  10. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  11. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  12. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
16 more
  1. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  2. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 117
  3. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignmentcited by 104
  4. 2024CRAG -- Comprehensive RAG Benchmarkcited by 94
  5. 2024RAGEval: Scenario Specific RAG Evaluation Dataset Generation Frameworkcited by 39
  6. 2024CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worldscited by 38
  7. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  8. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generationcited by 24
  9. 2024Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generationcited by 23
  10. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  11. 2024TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Modelscited by 21
  12. 2025Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysiscited by 17
  13. 2022MBTI Personality Prediction for Fictional Characters Using Movie Scriptscited by 14
  14. 2024CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agentscited by 10
  15. 2025RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrievalcited by 7
  16. 2025Role-Playing Evaluation for Large Language Modelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interactioncited by 3
  2. 2026GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testingcited by 3
  3. 2026From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agentscited by 1
  4. 2025Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval
  2. 2024From Persona to Personalization: A Survey on Role-Playing Language Agents
  3. 2025Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language Agent
  4. 2026Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects
  5. 2024Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
  6. 2024Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework
  7. 2024Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?
  8. 2026Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents