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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Ming, Huang, Xucheng, Yang, Chenghan, Peng, Xianhan, Wang, Haoxin, Liu, Yang, Jiang, Ling
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911044507533312
author Gong, Ming
Huang, Xucheng
Yang, Chenghan
Peng, Xianhan
Wang, Haoxin
Liu, Yang
Jiang, Ling
author_facet Gong, Ming
Huang, Xucheng
Yang, Chenghan
Peng, Xianhan
Wang, Haoxin
Liu, Yang
Jiang, Ling
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05330
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
Gong, Ming
Huang, Xucheng
Yang, Chenghan
Peng, Xianhan
Wang, Haoxin
Liu, Yang
Jiang, Ling
Computation and Language
Artificial Intelligence
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.
title MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.05330