更高满意度、更低成本：美团智能交互系统革命的技术报告
计算与语言
2026-01-15 v2 人工智能
摘要
提升客户体验是企业成功的关键，尤其当服务需求在规模和复杂度方面不断增长时。生成式人工智能和大型语言模型 (LLM) 已使智能交互系统能够提供高效、个性化且 24 小时不间断的支持。在实际应用中，智能交互系统面临若干挑战：(1) 构建冷启动训练的高质量数据困难，阻碍自我演化并提高劳动力成本。(2) 多轮对话性能仍不理想，由于意图理解不足、规则遵循不力以及方案提取不完整。(3) 业务规则频繁变更影响系统可操作性和可移植性，限制了低成本的扩展和适应性。(4) 单一 LLM 在复杂场景下仍不足，缺乏多智能体框架和有效协作导致过程不完整和服务质量受损。(5) 多轮对话的开放域自然缺乏统一的黄金答案，阻碍定量评估和持续优化。为应对这些挑战，我们引入面向工业应用的 WOWService—an intelligent interaction system。通过整合 LLM 和多智能体架构，WOWService 实现了自主任务管理和协作问题解决。具体而言，WOWService 聚焦核心模块，包括数据构建、通用能力提升、业务场景适配、多智能体协调和自动化评估。目前，WOWService 已在美团 App 上部署，实现关键指标显著提升，例如用户满意度指标 1 (USM 1) -27.53% 和用户满意度指标 2 (USM 2) +25.51%，展示了其在捕捉用户需求和推动个性化服务方面的有效性。
引用
@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}
}
备注
36 pages, 14 figures