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

ACL ARR 2026 January Submission1866 Authors

Keywords: Task-oriented Dialogue, Self-evolving Agents

Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in open-domain dialogues. However, their performance in service dialogues remains suboptimal, as these require agents to guide users toward specific business objectives while dynamically tracking states and adapting strategies. This gap stems from the scarcity of high-quality training data and the difficulty in simulating authentic, goal-oriented user behaviors. We propose \textbf{SEAD} (\textbf{S}elf-\textbf{E}volving \textbf{A}gent for Service \textbf{D}ialogue), 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 Simulator that focuses on realistic role-playing. This design ensures the environment provides adaptive training scenarios rather than acting as an unfair adversary.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: LLM agents

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 1866