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

2025-10-15

AI Summary

To address five key challenges in intelligent interactive systems—(1) difficulty in constructing cold-start data, (2) weak multi-turn intent understanding, (3) poor adaptability to dynamic business rules, (4) insufficient capability of single LLMs in handling complex service workflows, and (5) lack of open-domain evaluation—this paper proposes WOWService, an industrial-deployable multi-agent collaborative framework. Leveraging a task-driven multi-agent architecture integrated with large language models (LLMs), WOWService innovatively enables autonomous data generation, rule-aware dynamic scenario adaptation, joint intent–rule modeling, and automated multi-dimensional evaluation. Deployed in Meituan’s mobile application, it reduced user satisfaction metric USM1 by 27.53% and improved USM2 by 25.51%, significantly enhancing demand comprehension accuracy, service personalization, and system self-evolution capability—thereby enabling cost-effective, large-scale deployment.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Teamwork
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Addresses cold-start training data challenges and high labor costs
• Improves multi-turn dialogue performance and business rule adaptation
• Enhances multi-agent collaboration and automated evaluation in complex scenarios

Innovation

• LLMs and multi-agent architectures for autonomous task management
• Data construction and business adaptation for system evolution
• Automated evaluation and multi-agent coordination for service quality