Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems
Abstract
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 scenario adaptation, multi-agent coordination, and automated evaluation. Currently, WOWService is deployed on the Meituan App, achieving significant gains in key metrics, e.g., User Satisfaction Metric 1 (USM 1) -27.53% and User Satisfaction Metric 2 (USM 2) +25.51%, demonstrating its effectiveness in capturing user needs and advancing personalized service.
Cite
@article{arxiv.2510.13291,
title = {Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems},
author = {Xuxin Cheng and Ke Zeng and Zhiquan Cao and Linyi Dai and Wenxuan Gao and Fei Han and Ai Jian and Feng Hong and Wenxing Hu and Zihe Huang and Dejian Kong and Jia Leng and Zhuoyuan Liao and Pei Liu and Jiaye Lin and Xing Ma and Jingqing Ruan and Jiaxing Song and Xiaoyu Tan and Ruixuan Xiao and Wenhui Yu and Wenyu Zhan and Haoxing Zhang and Chao Zhou and Hao Zhou and Shaodong Zheng and Ruinian Chen and Siyuan Chen and Ziyang Chen and Yiwen Dong and Yaoyou Fan and Yangyi Fang and Yang Gan and Shiguang Guo and Qi He and Chaowen Hu and Binghui Li and Dailin Li and Xiangyu Li and Yan Li and Chengjian Liu and Xiangfeng Liu and Jiahui Lv and Qiao Ma and Jiang Pan and Cong Qin and Chenxing Sun and Wen Sun and Zhonghui Wang and Abudukelimu Wuerkaixi and Xin Yang and Fangyi Yuan and Yawen Zhu and Tianyi Zhai and Jie Zhang and Runlai Zhang and Yao Xu and Yiran Zhao and Yifan Wang and Xunliang Cai and Yangen Hu and Cao Liu and Lu Pan and Xiaoli Wang and Bo Xiao and Wenyuan Yao and Qianlin Zhou and Benchang Zhu},
journal= {arXiv preprint arXiv:2510.13291},
year = {2026}
}
Comments
36 pages, 14 figures