mlsanityData to 14 Oct 2026

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning

arXiv 2506.01748 ↗First posted 2 Jun 2025cs.CLcited by 14

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 1 more
Abstract (arXiv)

The advancement of Large Language Models (LLMs) has spurred significant interest in Role-Playing Agents (RPAs) for applications such as emotional companionship and virtual interaction. However, recent RPAs are often built on explicit dialogue data, lacking deep, human-like internal thought processes, resulting in superficial knowledge and style expression. While Large Reasoning Models (LRMs) can be employed to simulate character thought, their direct application is hindered by attention diversion (i.e., RPAs forget their role) and style drift (i.e., overly formal and rigid reasoning rather than character-consistent reasoning). To address these challenges, this paper introduces a novel Role-Aware Reasoning (RAR) method, which consists of two important stages: Role Identity Activation (RIA) and Reasoning Style Optimization (RSO). RIA explicitly guides the model with character profiles during reasoning to counteract attention diversion, and then RSO aligns reasoning style with the character and scene via LRM distillation to mitigate style drift. Extensive experiments demonstrate that the proposed RAR significantly enhances the performance of RPAs by effectively addressing attention diversion and style drift.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 42 of its 57 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

42 of 57 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Thinking Machines: A Survey of LLM based Reasoning Strategies13 Mar
  2. 2025Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents11 Mar
  3. 2025A Survey on Post-training of Large Language Models8 Mar
  4. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Models28 Feb
  5. 2025From System 1 to System 2: A Survey of Reasoning Large Language Models24 Feb
  6. 2025Reasoning Does Not Necessarily Improve Role-Playing Ability24 Feb
  7. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models16 Jan

Other references · 35

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  6. 2023Let's Verify Step by Stepcited by 3,789
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  8. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  9. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  10. 2025s1: Simple test-time scalingcited by 1,341
  11. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  12. 2025LIMO: Less is More for Reasoningcited by 498
23 more
  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  3. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 295
  4. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  5. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 175
  6. 2025SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilitiescited by 136
  7. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!cited by 132
  8. 2025Small Models Struggle to Learn from Strong Reasonerscited by 113
  9. 2023Multi-Party Chat: Conversational Agents in Group Settings with Humans and Modelscited by 54
  10. 2024Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agentcited by 52
  11. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agentscited by 50
  12. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 48
  13. 2024From Role-Play to Drama-Interaction: An LLM Solutioncited by 42
  14. 2024IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generationcited by 35
  15. 2024LLMs + Persona-Plug = Personalized LLMscited by 32
  16. 2025CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulationcited by 26
  17. 2023Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Personacited by 24
  18. 2023Editing Personality for Large Language Modelscited by 22
  19. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitiescited by 20
  20. 2024Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoningcited by 19
  21. 2024Identity-Driven Hierarchical Role-Playing Agentscited by 18
  22. 2025Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoningcited by 10
  23. 2024A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Stylescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 11.

14 papers.

Sort:

By area:

  1. 2026HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playingcited by 10
  2. 2026Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognitioncited by 6
  3. 2025MOA: Multi-Objective Alignment for Role-Playing Agentscited by 5
  4. 2026Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVRcited by 5
  5. 2026Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMscited by 5
  6. 2026Deriving Character Logic from Storyline as Codified Decision Treescited by 3
  7. 2025MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teachingcited by 2
  8. 2025Understanding Generalization in Role-Playing Models via Information Theorycited by 1
  9. 2026Codified Finite-state Machines for Role-playingcited by 1
  10. 2026Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimizationcited by 1
  11. 2026Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Modelscited by 0
  12. 2026Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agentcited by 0
2 more
  1. 2026BOOKMARKS: Efficient Active Storyline Memory for Role-playingcited by 0
  2. 2026OSPD: On-Policy Self-Distillation for Persona-Consistent Dialoguecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Role-Playing Agents Driven by Large Language Models: Current Status, Challenges, and Future Trends
  2. 2025RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward
  3. 2025Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language Agent
  4. 2024ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
  5. 2025Improving LLM Reasoning through Interpretable Role-Playing Steering
  6. 2024Thinking Before Speaking: A Role-playing Model with Mindset
  7. 2025Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
  8. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment