@inproceedings{huang-etal-2025-attributeforge,
    title = "{A}ttribute{F}orge: An Agentic {LLM} Framework for Automated Product Schema Modeling",
    author = "Huang, Yunhan  and
      Ramo, Klevis  and
      Iovine, Andrea  and
      Monteiro, Melvin  and
      Gokalp, Sedat  and
      Bakshi, Arjun  and
      Turalic, Hasan  and
      Kumar, Arsh  and
      Neumeier, Jona  and
      Yates, Ripley  and
      Monir, Rejaul  and
      Hartmann, Simon  and
      Manglik, Tushar  and
      Yakout, Mohamed",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.148/",
    pages = "2106--2121",
    ISBN = "979-8-89176-333-3",
    abstract = "Effective product schema modeling is fundamental to e-commerce success, enabling accurate product discovery and superior customer experience. However, traditional manual schema modeling processes are severely bottlenecked, producing only tens of attributes per month, which is insufficient for modern e-commerce platforms managing thousands of product types. This paper introduces AttributeForge, the first framework to automate end-to-end product schema modeling using Large Language Models (LLMs). Our key innovation lies in orchestrating 43 specialized LLM agents through strategic workflow patterns to handle the complex interdependencies in schema generation. The framework incorporates two novel components: MC2-Eval, a comprehensive validation system that assesses schemas against technical, business, and customer experience requirements; and AutoFix, an intelligent mechanism that automatically corrects modeling defects through iterative refinement. Deployed in production, AttributeForge achieves an 88$\times$ increase in modeling throughput while delivering superior quality: a 59.83{\%} Good-to-Good (G2G) conversion rate compared to 37.50{\%} for manual approaches. This significant improvement in both speed and quality enables e-commerce platforms to rapidly adapt their product schemas to evolving market needs."
}