Research paper

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

Research from AlibabaPublished by Association for Computational LinguisticsJul 2026PDF

Examine how simulated research trajectories can train an assistant to investigate questions about products.

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

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Jiangyuan Wang, Kejun Xiao, Huaipeng Zhao, Tao Luo, Xiaoyi Zeng. ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/v1/2026.acl-industry.96. Original PDF, unmodified.

CC BY 4.0

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

Related research.

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

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

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