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

• URL: http://arxiv.org/abs/2507.17147v1
• Date: Wed, 23 Jul 2025 02:26:33 GMT
• Title: CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
• Authors: Cheng Liu, Yifei Lu, Fanghua Ye, Jian Li, Xingyu Chen, Feiliang Ren, Zhaopeng Tu, Xiaolong Li,
• Abstract summary: Role-Playing Language Agents (RPLAs) have emerged as a significant application direction for Large Language Models (LLMs)<n>We introduce textbfCogDual, a novel RPLA adopting a textitcognize-then-respond reasoning paradigm.<n>By jointly modeling external situational awareness and internal self-awareness, CogDual generates responses with improved character consistency and contextual alignment.
• Score: 53.36917093757101
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 \emph{cognitive} mechanisms driving these behaviors. Inspired by cognitive psychology, we introduce \textbf{CogDual}, a novel RPLA adopting a \textit{cognize-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.

Related papers

• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward [7.9399136525335585]
  RAIDEN-R1 is a novel reinforcement learning framework that integrates Verifiable Role-Awareness Reward (VRAR)<n>We construct a high-quality, role-aware Chain-of-Thought dataset through multi-LLM collaboration.<n> Experiments on the RAIDEN benchmark demonstrate RAIDEN-R1's superiority.
  arXiv  Detail & Related papers  (2025-05-15T12:22:10Z)
• Relation-R1: Progressively Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relation Comprehension [31.952192907460713]
  Relation-R1 is the textitfirst unified relation comprehension framework.<n>It integrates cognitive chain-of-thought (CoT)-guided supervised fine-tuning (SFT) and group relative policy optimization ( GRPO)<n>Experiments on widely-used PSG and SWiG datasets demonstrate that Relation-R1 achieves state-of-the-art performance in both binary and textitN-ary relation understanding.
  arXiv  Detail & Related papers  (2025-04-20T14:50:49Z)
• Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training [60.38082979765664]
  CPRec is an All-domain Continual Pre-Training framework for Recommendation.<n>It holistically align LLMs with universal user behaviors through the continual pre-training paradigm.<n>We conduct experiments on five real-world datasets from two distinct platforms.
  arXiv  Detail & Related papers  (2025-04-11T20:01:25Z)
• A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning [7.923577336744156]
  We propose a dual-agent adversarial policy learning framework.<n>This framework allows agents to spontaneously learn the underlying semantics without introducing any human prior knowledge.<n>Experiments show that the adversarial process significantly improves the generalization performance of both agents.
  arXiv  Detail & Related papers  (2025-01-29T02:36:47Z)
• GRAM: Generalization in Deep RL with a Robust Adaptation Module [62.662894174616895]
  In this work, we present a framework for dynamics generalization in deep reinforcement learning.<n>We introduce a robust adaptation module that provides a mechanism for identifying and reacting to both in-distribution and out-of-distribution environment dynamics.<n>Our algorithm GRAM achieves strong generalization performance across in-distribution and out-of-distribution scenarios upon deployment.
  arXiv  Detail & Related papers  (2024-12-05T16:39:01Z)
• Rethinking ChatGPT's Success: Usability and Cognitive Behaviors Enabled by Auto-regressive LLMs' Prompting [5.344199202349884]
  We analyze the structure of modalities within both two types of Large Language Models and six task-specific channels during deployment. We examine the stimulation of diverse cognitive behaviors in LLMs through the adoption of free-form text and verbal contexts.
  arXiv  Detail & Related papers  (2024-05-17T00:19:41Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference [71.11416263370823]
  We propose a generative inverse reinforcement learning for user behavioral preference modelling. Our model can automatically learn the rewards from user's actions based on discriminative actor-critic network and Wasserstein GAN.
  arXiv  Detail & Related papers  (2021-05-03T13:14:25Z)
• Generalization Guarantees for Imitation Learning [6.542289202349586]
  Control policies from imitation learning can often fail to generalize to novel environments. We present rigorous generalization guarantees for imitation learning by leveraging the Probably Approximately Correct (PAC)-Bayes framework.
  arXiv  Detail & Related papers  (2020-08-05T03:04:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.