MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
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.
Ming Gong、Xucheng Huang、Chenghan Yang、Xianhan Peng、Haoxin Wang、Yang Liu、Ling Jiang
计算技术、计算机技术
Ming Gong,Xucheng Huang,Chenghan Yang,Xianhan Peng,Haoxin Wang,Yang Liu,Ling Jiang.MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents[EB/OL].(2025-07-07)[2025-07-17].https://arxiv.org/abs/2507.05330.点此复制
评论