mlsanityData to 14 Oct 2026

CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards

arXiv 2507.17147 ↗First posted 23 Jul 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Role-Playing Language Agents (RPLAs) have emerged as a significant application direction for Large Language Models (LLMs). Existing approaches typically rely on prompt engineering or supervised fine-tuning to enable models to imitate character behaviors in specific scenarios, but often neglect the underlying cognitive mechanisms driving these behaviors. Inspired by cognitive psychology, we introduce CogDual, a novel RPLA adopting a textitcognize-then-respond reasoning paradigm. By jointly modeling external situational awareness and internal self-awareness, CogDual generates responses with improved character consistency and contextual alignment. To further optimize the performance, we employ reinforcement learning with two general-purpose reward schemes designed for open-domain text generation. Extensive experiments on the CoSER benchmark, as well as Cross-MR and LifeChoice, demonstrate that CogDual consistently outperforms existing baselines and generalizes effectively across diverse role-playing tasks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 23 Jul 2025.

Builds on

28 of 41 references.

References · 28

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  6. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  7. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  8. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  9. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  10. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  12. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
16 more
  1. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluationcited by 143
  2. 2024Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewardingcited by 55
  3. 2021"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understandingcited by 48
  4. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 48
  5. 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoningcited by 42
  6. 2024Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Workscited by 38
  7. 2024Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?cited by 34
  8. 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32
  9. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  10. 2022Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mindcited by 19
  11. 2022Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characterscited by 16
  12. 2025Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimizationcited by 15
  13. 2025Reasoning Does Not Necessarily Improve Role-Playing Abilitycited by 14
  14. 2025Towards Enhanced Immersion and Agency for LLM-based Interactive Dramacited by 9
  15. 2025CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervisioncited by 6
  16. 2025Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playingcited by 10
  2. 2026Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effectscited by 3
  3. 2026DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graphcited by 2
  4. 2026BOOKMARKS: Efficient Active Storyline Memory for Role-playingcited by 0
  5. 2026Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agentscited by 0
  6. 2026PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agentscited 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. 2026Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models
  3. 2025Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
  4. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning
  5. 2025RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward
  6. 2026Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
  7. 2026RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents
  8. 2025Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation