KAPA: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understanding
Jiakai Tang, Shiqi Shen, ZhipengWang ZhipengWang, Gong Zhi, Xueyang Feng, Zexu Sun, Haoran Tan, Xu Chen
Abstract
Dialogue assistants have become ubiquitous in modern applications, fundamentally reshaping human daily communication patterns and information access behaviors. In real-world conversational interactions, however, user queries are often volatile, ambiguous, and diverse, making it difficult accurately and efficiently grasp the user’s underlying intentions. To address this challenge, we propose a simple yet effective deliberative agent framework that leverages human thought process to build high-level domain knowledge. To further achieve efficient knowledge accumulation and retrieval, we design a tree-structured knowledge base to store refined experience and data. Moreover, we construct a new benchmark, User-Intent-Understanding (UIU), which covers multi-domain, multi-tone, and sequential multi-turn personalized user queries. Extensive experiments demonstrate the effectiveness of our proposed method across multi-step evaluations.
BibTeX
@inproceedings{tang-etal-2025-kapa,
title = "{KAPA}: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understanding",
author = "Tang, Jiakai and
Shen, Shiqi and
ZhipengWang, ZhipengWang and
Zhi, Gong and
Feng, Xueyang and
Sun, Zexu and
Tan, Haoran and
Chen, Xu",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.319/",
doi = "10.18653/v1/2025.findings-acl.319",
pages = "6150--6166",
ISBN = "979-8-89176-256-5"
}