MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents
By: Ming Gong , Xucheng Huang , Chenghan Yang and more
Potential Business Impact:
Helps online shoppers by understanding pictures and words.
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.
Similar Papers
MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service
Computation and Language
Helps online shoppers get better help.
ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?
Computation and Language
Tests smart helpers for online shopping problems.
GridMind: LLMs-Powered Agents for Power System Analysis and Operations
Artificial Intelligence
AI helps power grids make smart choices faster.