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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dai, Yuqin, Gao, Ning, Zhang, Wei, Wang, Jie, Luo, Zichen, Wang, Jinpeng, Wang, Yujie, Wu, Ruiyuan, Wang, Chaozheng
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910190211694592
author Dai, Yuqin
Gao, Ning
Zhang, Wei
Wang, Jie
Luo, Zichen
Wang, Jinpeng
Wang, Yujie
Wu, Ruiyuan
Wang, Chaozheng
author_facet Dai, Yuqin
Gao, Ning
Zhang, Wei
Wang, Jie
Luo, Zichen
Wang, Jinpeng
Wang, Yujie
Wu, Ruiyuan
Wang, Chaozheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03548
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
Dai, Yuqin
Gao, Ning
Zhang, Wei
Wang, Jie
Luo, Zichen
Wang, Jinpeng
Wang, Yujie
Wu, Ruiyuan
Wang, Chaozheng
Computation and Language
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.
title SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
topic Computation and Language
url https://arxiv.org/abs/2602.03548