Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

• URL: http://arxiv.org/abs/2606.27025v1
• Date: Thu, 25 Jun 2026 13:34:47 GMT
• Title: Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
• Abstract summary: Psy-CoT is a chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps.<n>Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods.
• Score: 62.82109000444373
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant paradigm -- supervised fine-tuning -- encourages behavioral mimicry without deep, human-like internal thought processes, resulting in poor out-of-distribution generalization. Therefore, we propose \textbf{Psy-CoT}, a psychology-grounded chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps -- \emph{Interaction Perception}, \emph{Psychological Empathy}, and \emph{Logical Construction} -- so that the model \emph{thinks dynamically} from the profile rather than merely mimicking surface patterns. While structured reasoning provides a foundation, it alone is insufficient; reinforcement learning is essential to further align the model with character fidelity. However, we observe that under LLM-based reward models, both generic phrases that hack the reward model and genuinely role-specific phrases receive identical gradient signals -- this hacking accumulates over training, misleading the model into treating both as equally optimal choices. To address this, we propose \textbf{Role-Aware Policy Optimization (RAPO)}, which uses profile--token mutual information to weight gradients asymmetrically -- amplifying role-specific tokens under positive advantage while attenuating them under negative advantage. Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods, and RAPO consistently surpasses GRPO across multiple model scales.

Related papers

• CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents [53.765941044015854]
  We propose Character-Centric Group Relative Policy Optimization (CRPO), a framework designed to realign objectives with the role-playing task.<n>CRPO improves character distinctiveness through three mechanisms: decoupling task logic from stylistic rewards to resolve gradient conflicts, dynamically adapting optimization constraints based on character complexity, and utilizing generic responses as negative baselines to prevent the model from reverting to a common distribution.
  arXiv  Detail & Related papers  (2026-05-25T07:15:38Z)
• Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges [87.04241991512386]
  We propose the Proxy Compression Hypothesis (PCH) as a unifying framework for understanding reward hacking.<n>Under this view, reward hacking arises from the interaction of objective compression, optimization amplification, and evaluator--policy co-adaptation.<n>This perspective unifies empirical phenomena across RLHF, RLAIF, and RLVR regimes, and explains how local shortcut learning can generalize into broader forms of misalignment.
  arXiv  Detail & Related papers  (2026-04-15T08:11:34Z)
• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• A First-Order Logic-Based Alternative to Reward Models in RLHF [0.0]
  Reinforcement Learning from Human Feedback plays a crucial role in aligning large language models with human values and preferences.<n>Existing approaches rely heavily on reward models to guide language models toward human-aligned behaviors.<n>We propose a logic-similarity-based reward mechanism as an alternative to conventional reward modeling.
  arXiv  Detail & Related papers  (2025-12-16T05:15:17Z)
• RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems [85.16327248973387]
  We develop RoleRM, a reward model trained with Continuous Implicit Preferences (CIP)<n>We show RoleRM surpasses strong open- and closed-source reward models by over 24% on average.<n>Our findings highlight the importance of continuous preference representation and annotation consistency, establishing a foundation for subjective alignment in human-centered dialogue systems.
  arXiv  Detail & Related papers  (2025-12-11T12:04:46Z)
• CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards [53.36917093757101]
  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.
  arXiv  Detail & Related papers  (2025-07-23T02:26:33Z)
• Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning [7.836439251883518]
  We propose a novel framework named textbfunderlinePersona-Aware textbfunderlineContrastive textbfunderlineLearning (PCL) to align model role-playing behavior.<n>We show that PCL significantly outperform vanilla LLMs under automatic evaluation methods and human expert evaluation.
  arXiv  Detail & Related papers  (2025-03-22T06:12:34Z)

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.