让角色扮演机器人更懂角色，减少出戏行为。
Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
- 通过10个角色特质标签构建认知结构
- 引用参考回答提升探索与表现
- 按角色类型动态调整奖励，适配多样角色
当前角色扮演智能体多依赖表面行为模仿，缺乏内在认知一致性，复杂情境下常出现不符合角色的错误。为此，我们提出Character-R1框架，提供全面可验证的奖励信号以实现有效角色感知推理。该框架包含三个核心设计：(1) 认知焦点奖励，强制基于10个角色元素（如世界观）的显式标签分析，以结构化内部认知；(2) 参考引导奖励，利用重叠度指标与参考响应作为优化锚点，增强探索与性能；(3) 角色条件奖励归一化，根据角色类别调整奖励分布，确保在异质角色间稳健优化。大量实验表明，Character-R1在知识、记忆等方面显著优于现有方法。
原文摘要 · Abstract (English)
Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we propose Character-R1, a framework designed to provide comprehensive verifiable reward signals for effective role-aware reasoning, which are missing in recent studies. Specifically, our framework comprises three core designs: (1) Cognitive Focus Reward, which enforces explicit label-based analysis of 10 character elements (e.g., worldview) to structure internal cognition; (2) Reference-Guided Reward, which utilizes overlap-based metrics with reference responses as optimization anchors to enhance exploration and performance; and (3) Character-Conditioned Reward Normalization, which adjusts reward distributions based on character categories to ensure robust optimization across heterogeneous roles. Extensive experiments demonstrate that Character-R1 significantly outperforms existing methods in knowledge, memory and others.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。