Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems

作者：Xuxin Cheng, Ke Zeng, Zhigang Cao, Dai, Linyi, Gao, Wenxuan, Fei Han, Ai Jian, Feng Hong, Wenxing Hu, Huang, Zihe, Kong, Dejian, Leng, Jia, Zhengbu Liao, Pei‐Shan Liu, Jiaye Lin, Xing Ma, Jingqing Ruan, Song, Jiaxing, Xiaoyu Tan, Ruixuan Xiao, Wenhui Yu, Wenyu Zhan, Haoxing Zhang, Chao Zhou, Hao Zhou, Shaodong Zheng, Chen, Ruinian, Siyuan Chen, Ziyang Chen, Dong, Yiwen, You Hong Fan, Y. Fang, Gan Yang, Shiguang Guo, Qi He, Chaolu Hu, Binghui Li, Dailin Li, Xiangyu Li, Yan Li, Chengjian Liu, Xiangfeng Liu, Jiahui Lv, Qiang Ma, Jiang Pan, Cong Qin, Chenxing Sun, Wen Sun, Zhonghui Wang, Abudukelimu Wuerkaixi, Xin Yang, Fan Yuan, Yawen Zhu, Tianyi Zhai, Jie Zhang, Zhang, Runlai, Yao Xu, Yiran Zhao, Yifan Wang, Xunliang Cai, Yue Hu, Liu Cao, Pan Lu, Xiaoli Wang, Bo Xiao, Wenzhi Yao, Qu Zhou, Zhu, Benchang · 发表于：arXiv (Cornell University) · 年份：2025 · DOI：10.48550/arxiv.2510.13291 · 研究领域：Big Data and Business Intelligence

Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction systems to deliver efficient, personalized, and 24/7 support. In practice, intelligent interaction systems encounter several challenges: (1) Constructing high-quality data for cold-start training is difficult, hindering self-evolution and raising labor costs. (2) Multi-turn dialogue performance remains suboptimal due to inadequate intent understanding, rule compliance, and solution extraction. (3) Frequent evolution of business rules affects system operability and transferability, constraining low-cost expansion and adaptability. (4) Reliance on a single LLM is insufficient in complex scenarios, where the absence of multi-agent frameworks and effective collaboration undermines process completeness and service quality. (5) The open-domain nature of multi-turn dialogues, lacking unified golden answers, hampers quantitative evaluation and continuous optimization. To address these challenges, we introduce WOWService, an intelligent interaction system tailored for industrial applications. With the integration of LLMs and multi-agent architectures, WOWService enables autonomous task management and collaborative problem-solving. Specifically, WOWService focuses on core modules including data construction, general capability enhancement, business scenari...