English

MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents

Computation and Language 2025-07-09 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2507.05330,
  title  = {MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents},
  author = {Ming Gong and Xucheng Huang and Chenghan Yang and Xianhan Peng and Haoxin Wang and Yang Liu and Ling Jiang},
  journal= {arXiv preprint arXiv:2507.05330},
  year   = {2025}
}
R2 v1 2026-07-01T03:50:06.845Z