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

arXiv: https://arxiv.org/abs/2507.17147 · HTML: https://mlsanity.com/paper/2507.17147/

## 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 (most cited first, 28 of 28)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding](https://mlsanity.com/paper/2411.04282/) (2024)
- ["Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding](https://mlsanity.com/paper/2109.05438/) (2021)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning](https://mlsanity.com/paper/2504.19162/) (2025)
- [Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works](https://mlsanity.com/paper/2404.12726/) (2024)
- [Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?](https://mlsanity.com/paper/2404.12138/) (2024)
- [LLMs are Also Effective Embedding Models: An In-depth Overview](https://mlsanity.com/paper/2412.12591/) (2024)
- [Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning](https://mlsanity.com/paper/2503.17662/) (2025)
- [Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind](https://mlsanity.com/paper/2211.04684/) (2022)
- [Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters](https://mlsanity.com/paper/2211.06869/) (2022)
- [Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization](https://mlsanity.com/paper/2502.01652/) (2025)
- [Reasoning Does Not Necessarily Improve Role-Playing Ability](https://mlsanity.com/paper/2502.16940/) (2025)
- [Towards Enhanced Immersion and Agency for LLM-based Interactive Drama](https://mlsanity.com/paper/2502.17878/) (2025)
- [CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision](https://mlsanity.com/paper/2503.20840/) (2025)
- [Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents](https://mlsanity.com/paper/2503.08193/) (2025)

## Built on by (most cited first, 6 of 6)

- [HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing](https://mlsanity.com/paper/2601.21459/) (2026)
- [Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects](https://mlsanity.com/paper/2603.03915/) (2026)
- [DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graph](https://mlsanity.com/paper/2608.05170/) (2026)
- [BOOKMARKS: Efficient Active Storyline Memory for Role-playing](https://mlsanity.com/paper/2605.14169/) (2026)
- [Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents](https://mlsanity.com/paper/2609.28609/) (2026)
- [PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents](https://mlsanity.com/paper/2609.34372/) (2026)

## 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.