mlsanityData to 14 Oct 2026

BOOKMARKS: Efficient Active Storyline Memory for Role-playing

arXiv 2605.14169 ↗First posted 13 May 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Memory systems are critical for role-playing agents (RPAs) to maintain long-horizon consistency. However, existing RPA memory methods (e.g., profiling) mainly rely on incremental summarization, whose compression discards details which become inaccessible to subsequent grounding. To address this issue, we propose a search-based memory framework called textbfunderlineBOOKMARKS for active grounding, which retains access to the full preceding storyline and collects task-relevant information on demand. Since summarizing the preceding storyline anew for each grounding request incurs substantial redundant computation, BOOKMARKS introduces passive updating to reuse earlier search results as checkpoints. Each bookmark represents the content about a particular aspect (section) of story information at a specific synchronization point. For current task, BOOKMARKS searches for only useful contents, reuses existing semantically equivalent bookmarks or initializes new ones, and synchronizes the selected ones from their stored checkpoints to the current scene. A reused bookmark thus only needs to process the newly observed storyline suffix, avoiding repeated synchronization. We evaluate BOOKMARKS across six narrative artifacts involving 47 characters and 9,537 test cases against non-active grounding baselines, covering next-action prediction and challenging, human-authored reasoning questions from a mystery game. BOOKMARKS improves next-action fidelity in a five-dimensional evaluation (emotion, intent, causality, position, and content) and raises mystery-game reasoning accuracy from 39.44% to 45.42% over the strongest baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 55 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

48 of 55 references.

References · 48

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  2. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  3. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  4. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 367
  5. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 345
  6. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  7. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  8. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  9. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  10. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 175
  11. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluationcited by 143
  12. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignmentcited by 104
36 more
  1. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 97
  2. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  3. 2023Learning to Retrieve In-Context Examples for Large Language Modelscited by 60
  4. 2024Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agentcited by 52
  5. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agentscited by 50
  6. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Modelscited by 43
  7. 2025SCORE: Story Coherence and Retrieval Enhancement for AI Narrativescited by 42
  8. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40
  9. 2025Learning to Reason for Long-Form Story Generationcited by 34
  10. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  11. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
  12. 2025OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personascited by 25
  13. 2023LARP: Language-Agent Role Play for Open-World Gamescited by 24
  14. 2024SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agentcited by 24
  15. 2024TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Modelscited by 22
  16. 2023RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Modelscited by 21
  17. 2025StoryWriter: A Multi-Agent Framework for Long Story Generationcited by 19
  18. 2024Mitigating Hallucination in Fictional Character Role-Playcited by 18
  19. 2024Identity-Driven Hierarchical Role-Playing Agentscited by 18
  20. 2025RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Followingcited by 18
  21. 2025Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoningcited by 14
  22. 2025RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Rewardcited by 13
  23. 2025RPGBENCH: Evaluating Large Language Models as Role-Playing Game Enginescited by 12
  24. 2024Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Frameworkcited by 10
  25. 2025PsyPlay: Personality-Infused Role-Playing Conversational Agentscited by 9
  26. 2025PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?cited by 9
  27. 2025MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialoguescited by 8
  28. 2025RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrievalcited by 7
  29. 2024Grounded Answers for Multi-agent Decision-making Problem through Generative World Modelcited by 6
  30. 2025CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewardscited by 6
  31. 2024ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learningcited by 5
  32. 2025Codifying Character Logic in Role-Playingcited by 5
  33. 2025PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMscited by 5
  34. 2026Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMscited by 5
  35. 2025RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systemscited by 4
  36. 2026Deriving Character Logic from Storyline as Codified Decision Treescited by 3

Built on by

Not cited yet.