发表机构
ModelsLive Inc.（ModelsLive公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出人格支持范式，构建了DSD数据集、DeepSupport系统及Ekova智能体，经OrthoTune训练的模型在相关指标上较基线平均提升16.3%。
AI 中文摘要
情感支持（ES）系统长期以来都以缓解用户当下的情绪困扰为单一优化目标。我们认为，帮助用户更清晰地认识自我是一项互补需求，它定义了一种被我们称为人格支持（PS）的独特范式。人格支持并非心理咨询或临床干预，其目标是认知清晰度与自我表达，而非症状缓解或诊断。我们将这一范式落实为三个层级：首先，我们推出DSD，这是一个包含8590个样本的中文自我发现人格支持数据集，通过五个最小单元（Coach、Warm、Tsukkomi、Real和Gonzo）的真实纵向交互收集而成；其次，我们构建DeepSupport，这是一个多人格的人格支持系统，采用OrthoTune训练，OrthoTune是一种专为人格支持设计的框架，具备风格特定适配器和风格一致性正则化器；最后，我们将DeepSupport的五种人格统一为Ekova，这是一个具备统一跨会话记忆层的持久人格支持智能体，支持自适应路由和用户自定义的人格选择。实验表明，经OrthoTune训练的模型在所有指标上较最强的基于提示的基线平均相对提升16.3%。代码可在该https URL获取。
英文摘要
Emotional Support (ES) systems have long optimized a single objective: alleviating the user's emotional distress in the moment. We argue that a complementary need, helping users see themselves more clearly, defines a distinct paradigm we call Personality Support (PS). PS is not counseling or clinical intervention: it targets cognitive clarity and self-articulation, not symptom relief or diagnosis. We instantiate this paradigm in three layers. First, we present DSD, a Chinese self-discovery PS Dataset of 8,590 samples collected through real longitudinal interaction across five minimal units, Coach, Warm, Tsukkomi, Real, and Gonzo. Second, we build DeepSupport, a multi-persona PS system trained with OrthoTune, a PS-tailored framework with style-specific adapters and a style-consistency regularizer. Third, we unify the five DeepSupport personas into Ekova, a persistent personality-support agent with a unified cross-session memory layer, supporting both adaptive routing and user-customized persona selection. Experiments show that OrthoTune-trained models outperform all baselines with an average relative gain of 16.3% across all metrics over the strongest prompt-based baseline. Code is available at https://github.com/Yukyin/Ekova.
CommentsAccepted to the COLM 2026 Lifelong Agents Workshop
