ESC-Skills: 发现并自我进化情感支持对话技能
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
AI总结：
提出ESC-Skills框架，通过干预单元建模支持交互并构建技能库，结合多轮廓自我进化机制，提升情感支持对话的可解释性、可控性和效果。
摘要：
现有的情感支持对话（ESC）系统主要依赖于端到端的回复生成或粗粒度的策略监督，可解释性有限，且对系统性的技能提升支持不足。我们提出ESC-Skills，一个以技能为中心的框架，能够发现并自我进化可执行的情感支持技能。我们首先将局部支持交互建模为干预单元（IUs），捕捉求助者状态、支持干预和回复后情绪变化之间的状态-动作-结果动态。基于从成功和失败的ESC对话中提取的IUs，我们构建了ESC-Skills库，这是一个包含干预指导、适用条件、预期结果和潜在风险的可执行情感支持技能仓库。为了进一步提升鲁棒性，我们引入了一个多轮廓自我进化精炼框架，其中ESC代理在SAGE评估下与多种模拟求助者轮廓进行交互。分析由此产生的交互轨迹，以识别缺失的技能、不安全的干预和特定轮廓的失败模式，然后通过基于模拟的验证来精炼技能库。实验结果表明，ESC-Skills在提升回复质量和对话层面的情感结果的同时，提供了更可解释和可控的支持行为。我们将发布代码、提示和ESC-Skills库，网址为https://github.com/aliyun/qwen-dianjin。
英文摘要：
Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little support for systematic skill improvement. We propose ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills. We first model localized support interactions as Intervention Units (IUs), which capture state--action--outcome dynamics between seeker states, support interventions, and post-response emotional changes. Based on IUs extracted from both successful and failed ESC dialogues, we construct the ESC-Skills Bank, a repository of executable emotional support skills containing intervention guidance, applicability conditions, expected outcomes, and potential risks. To further improve robustness, we introduce a multi-profile self-evolutionary refinement framework in which an ESC agent interacts with diverse simulated seeker profiles under SAGE evaluation. The resulting interaction traces are analyzed to identify missing skills, unsafe interventions, and profile-specific failure patterns, which are then used to refine the Skills Bank through simulation-based verification. Experimental results demonstrate that ESC-Skills improves both response-level quality and dialogue-level emotional outcomes while providing more interpretable and controllable support behaviors. We will release the code, prompts, and ESC-Skills Bank at https://github.com/aliyun/qwen-dianjin.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
