用多模态大模型打造电商客服代理，提升复杂问题处理能力。
MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
- 构建基于CoALA框架的模块化智能体，融合记忆、决策与执行功能。
- 真实部署中复杂查询解决率提升93.53%，用户满意度与运营效率显著改善。
- 开源设计，适合需要高阶视觉-文本理解的电商客服系统开发者。
大语言模型在电商客服领域取得进展，但在复杂多模态场景下仍受限。本文提出MindFlow，首个面向电商的开源多模态大模型智能体，基于CoALA框架构建，集成记忆、决策与行动模块，并采用'MLLM-as-Tool'策略实现高效视觉-文本推理。通过在线A/B测试与模拟消融实验评估，结果显示其在处理复杂查询、提升用户满意度及降低运营成本方面表现突出，在真实部署中实现93.53%的相对性能提升。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) have enabled new applications in e-commerce customer service. However, their capabilities remain constrained in complex, multimodal scenarios. We present MindFlow, the first open-source multimodal LLM agent tailored for e-commerce. Built on the CoALA framework, it integrates memory, decision-making, and action modules, and adopts a modular "MLLM-as-Tool" strategy for effect visual-textual reasoning. Evaluated via online A/B testing and simulation-based ablation, MindFlow demonstrates substantial gains in handling complex queries, improving user satisfaction, and reducing operational costs, with a 93.53% relative improvement observed in real-world deployments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。