Metraipolis › archive › dc_e82d7ca54d2f
RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce — arXiv:2609.38974
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38974
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:42:25.095Z
- SHA-256 of the archived text
ebccc370532dc99e74ff36dc32ad75fe6a44e8d8070b714c4f7669f707de5cc5- Stable URL of this page
https://metraipolis.com/documento/dc_e82d7ca54d2f
How to cite
RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce — arXiv:2609.38974 — arXiv (en), https://arxiv.org/abs/2609.38974 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e82d7ca54d2f (Metraipolis archive dc_e82d7ca54d2f, sha256 ebccc370532dc99e74ff36dc32ad75fe6a44e8d8070b714c4f7669f707de5cc5)
BibTeX
@misc{dce82d7ca54d2f,
title = {RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce — arXiv:2609.38974},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38974},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e82d7ca54d2f; sha256 ebccc370532dc99e74ff36dc32ad75fe6a44e8d8070b714c4f7669f707de5cc5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38974. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are reshaping ecommerce from static recommenders into interactive shopping assistants, yet real-world shopping requires session-level decision support: users reveal and revise constraints, coordinate multiple goals, and expect product-grounded recommendations over a full conversation. Existing benchmarks are mostly outcome-oriented or execution-oriented, leaving this evolving decision process under-evaluated. We introduce REALWORLDSHOP, a benchmark built on 3.28M grounded products, structured shopping episodes, a profile-grounded and actioncontrolled user simulator, and role-play evaluation. Our analysis shows that current systems produce locally plausible responses but struggle with state tracking, constraint updating, and grounded convergence, especially under ambiguous intent, bundle, and multi-intent scenarios. We further propose REALSHOP_AGENT, an executable session-control framework with explicit state management, shopping-flow control, catalog-grounded retrieval, and runtime guards. Experiments show that REALSHOP_AGENT consistently outperforms strong baselines on REALWORLDSHOP. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.38974 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T12:14:13.724Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).