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

TL;DR

SEAD introduces a self-evolving framework for service dialogue agents that learns effectively without extensive human data, improving task success and dialogue efficiency.

Contribution

SEAD decouples user modeling into a profile controller and role-play model, enabling adaptive training without large-scale human annotations.

Findings

SEAD outperforms open-source foundation models in task completion.

SEAD improves dialogue efficiency by 11.1%.

Code is available at https://github.com/Da1yuqin/SEAD.

Abstract

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.