mlsanityData to 14 Oct 2026

MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service

arXiv 2507.18884 ↗First posted 25 Jul 2025cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

also in 1 more
Abstract (arXiv)

High-quality dialogue is crucial for e-commerce customer service, yet traditional intent-based systems struggle with dynamic, multi-turn interactions. We present MindFlow+, a self-evolving dialogue agent that learns domain-specific behavior by combining large language models (LLMs) with imitation learning and offline reinforcement learning (RL). MindFlow+ introduces two data-centric mechanisms to guide learning: tool-augmented demonstration construction, which exposes the model to knowledge-enhanced and agentic (ReAct-style) interactions for effective tool use; and reward-conditioned data modeling, which aligns responses with task-specific goals using reward signals. To evaluate the model's role in response generation, we introduce the AI Contribution Ratio, a novel metric quantifying AI involvement in dialogue. Experiments on real-world e-commerce conversations show that MindFlow+ outperforms strong baselines in contextual relevance, flexibility, and task accuracy. These results demonstrate the potential of combining LLMs tool reasoning, and reward-guided learning to build domain-specialized, context-aware dialogue systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 29 of its 52 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

29 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  2. 2024From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models5 Jan

Other references · 27

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2023A Survey of Large Language Modelscited by 2,576
  7. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  8. 2023A Comprehensive Overview of Large Language Modelscited by 648
  9. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  10. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 256
  11. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 231
  12. 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
15 more
  1. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 185
  2. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  3. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 156
  4. 2017Natural Language Processing: State of The Art, Current Trends and Challengescited by 114
  5. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 96
  6. 2023Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizationscited by 61
  7. 2024CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMscited by 17
  8. 2020Meaningful Answer Generation of E-Commerce Question-Answeringcited by 16
  9. 2024A survey on fairness of large language models in e-commerce: progress, application, and challengecited by 10
  10. 2024Language-Conditioned Offline RL for Multi-Robot Navigationcited by 9
  11. 2024Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rolloutscited by 6
  12. 2024Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intentscited by 5
  13. 2022Natural Language Processing in Customer Service: A Systematic Reviewcited by 4
  14. 2021Distantly Supervised Transformers For E-Commerce Product QAcited by 3
  15. 2024LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemblecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
  2. 2025MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Service
  3. 2026RL-ADA: A World-Feedback Framework for Adversarially Robust Enterprise Dialogue Agents
  4. 2026Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
  5. 2026Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
  6. 2026One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems
  7. 2026EComStage: Stage-wise and Orientation-specific Benchmarking for Large Language Models in E-commerce
  8. 2025Benchmarking and Learning Real-World Customer Service Dialogue