Metraipolis › archive › dc_f23fdf12bf16
Learning from Online User Feedback for Shopping Agents — arXiv:2608.11604
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11604
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:15:24.929Z
- SHA-256 of the archived text
8fb48245782d7413f5fd794f641734491a1eaab5858d1ca4a3fd1b757b67093d- Stable URL of this page
https://metraipolis.com/documento/dc_f23fdf12bf16
How to cite
Learning from Online User Feedback for Shopping Agents — arXiv:2608.11604 — arXiv (en), https://arxiv.org/abs/2608.11604 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f23fdf12bf16 (Metraipolis archive dc_f23fdf12bf16, sha256 8fb48245782d7413f5fd794f641734491a1eaab5858d1ca4a3fd1b757b67093d)
BibTeX
@misc{dcf23fdf12bf16,
title = {Learning from Online User Feedback for Shopping Agents — arXiv:2608.11604},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11604},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f23fdf12bf16; sha256 8fb48245782d7413f5fd794f641734491a1eaab5858d1ca4a3fd1b757b67093d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11604. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents. However, existing approaches primarily rely on offline training signals, such as user-item interactions or synthetic preference data, while largely overlooking the rich supervision contained in users' natural conversational feedback. Moreover, the available online feedback is heterogeneous, sparse, and noisy, making it difficult to transform into reliable learning signals automatically. To address these challenges, we propose LOFA, a framework that enables shopping agents to learn directly from real online interaction logs without human annotation. LOFA combines reinforcement learning over verifiable purchase outcomes with feedback-aware on-policy distillation, which identifies users'in-dialogue directives and converts them into dense token-level supervision. These complementary objectives capture both collaborative behavioral patterns and user-specific preferences. Extensive experiments on real-world e-commerce logs demonstrate that LOFA consistently improves recommendation quality, response helpfulness, and user-satisfaction alignment over strong baselines, highlighting the effectiveness of learning shopping agents from real online user feedback. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.11604 — 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 2026-10-19T05:08:46.633Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).