Research paper

SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants

Research from AlibabaPublished by Association for Computational LinguisticsOct 2026PDF

Explore how an e-commerce assistant can develop and reuse skills for questions that include product images.

SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Yimin Hu, Mengtao Xu, Hao Guo, Yuheng Song, Xiaoyong Zhu, Bo Zheng. SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track. © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/2026.emnlp-industry.63. Original PDF, unmodified.

CC BY 4.0

SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants

Related research.

EAGER: Enrich-and-Align Generative Query Recommendation from Clicked Items in E-commerce Search

ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation

Quality Over Clicks: Iterative Reinforcement Learning for Early-Stage E-Commerce Query Suggestion