mlsanityData to 14 Oct 2026

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

arXiv 2510.13291 ↗First posted 15 Oct 2025cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 48 of its 73 references that are in the map. First posted on arXiv 15 Oct 2025.

Builds on

48 of 73 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2017Proximal Policy Optimization Algorithmscited by 15,215
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  8. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  10. 2024Qwen2.5 Technical Reportcited by 4,942
  11. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  12. 2017Deep reinforcement learning from human preferencescited by 3,912
36 more
  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2024MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialoguescited by 250
  4. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 239
  5. 2023Continual Pre-training of Language Modelscited by 198
  6. 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systemscited by 183
  7. 2024RegMix: Data Mixture as Regression for Language Model Pre-trainingcited by 177
  8. 2018The Design and Implementation of XiaoIce, an Empathetic Social Chatbotcited by 172
  9. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  10. 2025RM-R1: Reward Modeling as Reasoningcited by 154
  11. 2024Benchmarking Complex Instruction-Following with Multiple Constraints Compositioncited by 152
  12. 2024Generative Reward Modelscited by 148
  13. 2024The Revolution of Multimodal Large Language Models: A Surveycited by 137
  14. 2024InFoBench: Evaluating Instruction Following Ability in Large Language Modelscited by 135
  15. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 132
  16. 2024Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsalcited by 118
  17. 2024Critique-out-Loud Reward Modelscited by 106
  18. 2024MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Modelscited by 81
  19. 2024Self-Generated Critiques Boost Reward Modeling for Language Modelscited by 71
  20. 2024CFBench: A Comprehensive Constraints-Following Benchmark for LLMscited by 67
  21. 2025Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Modelscited by 62
  22. 2025LongCat-Flash Technical Reportcited by 58
  23. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 57
  24. 2025The Best Instruction-Tuning Data are Those That Fitcited by 52
  25. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Startcited by 41
  26. 2023Large Language Model Instruction Following: A Survey of Progresses and Challengescited by 31
  27. 2025MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversationcited by 29
  28. 2024MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactionscited by 26
  29. 2023On The Fragility of Learned Reward Functionscited by 21
  30. 2024Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Modelscited by 20
  31. 2024Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Modelscited by 16
  32. 2025Optimizing Pretraining Data Mixtures with LLM-Estimated Utilitycited by 15
  33. 2025TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Modelscited by 13
  34. 2024Research on emotionally intelligent dialogue generation based on automatic dialogue systemcited by 5
  35. 2024Contact Complexity in Customer Servicecited by 2
  36. 2025Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisonscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarioscited by 10
  2. 2026M3Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactionscited by 5
  3. 2026NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harnesscited by 4
  4. 2026Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agentscited by 2
  5. 2026Position: Multi-Agent Systems Should Prioritize Concurrency Controlcited by 1
  6. 2026cMoLLM at Scale: Horizontal Scaling Laws for Mixture-of-LLMscited by 0
  7. 2026From High Recall to High Utility: Dataset-Adaptive Post-Processing of LLM-Generated Customer Intentscited by 0