SEAD：面向多轮服务对话的自演进智能体

摘要

大语言模型在开放域对话中展现出卓越能力，但在服务型对话场景下，现有方法因依赖嘈杂低质的人类对话数据而表现欠佳。这一局限源于数据稀缺性以及模拟真实目标导向用户行为的困难。为解决这些问题，我们提出SEAD（服务对话自演进智能体框架），该框架使智能体无需大规模人工标注即可学习有效策略。SEAD将用户建模解耦为两个组件：用于生成多样化用户状态以管理训练课程的档案控制器，以及专注于逼真角色扮演的用户模拟模型。该设计确保环境能提供自适应训练场景，而非充当不公平的对抗方。实验表明，SEAD显著优于开源基础模型与闭源商业模型，任务完成率提升17.6%，对话效率提高11.1%。代码已开源：https://github.com/Da1yuqin/SEAD。

English

Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This limitation arises from data scarcity and the difficulty of simulating authentic, goal-oriented user behaviors. To address these issues, we propose SEAD (Self-Evolving Agent for Service Dialogue), a framework that enables agents to learn effective strategies without large-scale human annotations. SEAD decouples user modeling into two components: a Profile Controller that generates diverse user states to manage training curriculum, and a User Role-play Model that focuses on realistic role-playing. This design ensures the environment provides adaptive training scenarios rather than acting as an unfair adversary. Experiments demonstrate that SEAD significantly outperforms Open-source Foundation Models and Closed-source Commercial Models, improving task completion rate by 17.6% and dialogue efficiency by 11.1%. Code is available at: https://github.com/Da1yuqin/SEAD.

SEAD：面向多轮服务对话的自演进智能体

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue

摘要

Support