As web platforms evolve towards greater personalization and emotional complexity, conversational agents must transcend superficial empathy to demonstrate identity-aware emotional reasoning. However, existing systems face two limitations: (1) reliance on situation-centric datasets lacking persistent user identity, which hampers the capture of personalized affective nuances; and (2) dependence on opaque, coarse reward signals that hinder development of verifiable empathetic reasoning. To address these gaps, we introduce KardiaBench, a large-scale user-grounded benchmark comprising 178,080 QA pairs across 22,080 multi-turn conversations anchored to 671 real-world profiles. The dataset is constructed via a model-in-the-loop pipeline with iterative rubric-guided refinement to ensure psychological plausibility and persona consistency. This progressive empathy pipeline that integrates user comprehension, contextual reasoning, and emotion perception into conversations, followed by iterative critique and rubric-based refinement to ensure psychological plausibility, emotional fidelity, and persona consistency. Building on this, we propose Kardia-R1, a framework that trains models for interpretable, stepwise empathetic cognition. Kardia-R1 leverages Rubric-as-Judge Empathetic Reinforcement Learning (Rubric-ERL), a GRPO-based method that uses explainable, human-aligned rubric rewards to tightly couple user understanding, emotional inference, and supportive response generation. Extensive experiments across four LLM backbones demonstrate that Kardia-R1 consistently outperforms othet methods in emotion accuracy, empathy, relevance, persona consistency, and safety. Our dataset and model will be released at https://github.com/JhCircle/Kardia-R1.

翻译：随着网络平台向更高程度的个性化和情感复杂性演进，对话智能体必须超越表面的共情，展现出基于身份识别的情绪推理能力。然而，现有系统面临两大局限：(1) 依赖以情境为中心、缺乏持久用户身份的数据集，这阻碍了对个性化情感细微差异的捕捉；(2) 依赖不透明、粗糙的奖励信号，这妨碍了可验证的共情推理能力的发展。为解决这些不足，我们引入了KardiaBench，一个大规模、基于真实用户的基准测试集，包含基于671个真实世界个人档案的22,080轮多轮对话，共计178,080个问答对。该数据集通过一个模型在环的流程构建，并经过迭代的、基于量表的指导优化，以确保心理合理性和人物一致性。这个渐进式共情流程将用户理解、情境推理和情感感知整合到对话中，随后通过迭代的评判和基于量表的优化，来确保心理合理性、情感保真度和人物一致性。在此基础上，我们提出了Kardia-R1，一个训练模型以实现可解释、分步式共情认知的框架。Kardia-R1利用了基于量表的评判共情强化学习，这是一种基于GRPO的方法，它使用可解释的、与人类对齐的量表奖励，将用户理解、情绪推断和支持性回应生成紧密耦合。在四种大语言模型骨干上的大量实验表明，Kardia-R1在情感准确性、共情度、相关性、人物一致性和安全性方面持续优于其他方法。我们的数据集和模型将在 https://github.com/JhCircle/Kardia-R1 发布。