Metraipolis › archive › dc_fde368fdd192

E-GenRM: Generative Reward Modeling for Open-Ended E-Commerce Shopping Agents — arXiv:2611.03008

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03008
License (as archived): CC0-1.0
Archived: 2026-11-03T11:39:43.243Z
SHA-256 of the archived text: 43b89f7a37f9cf83b889be74f155412734a1b4071cd8cfe41e0b93d28aac60d5
Stable URL of this page: https://metraipolis.com/documento/dc_fde368fdd192

How to cite

E-GenRM: Generative Reward Modeling for Open-Ended E-Commerce Shopping Agents — arXiv:2611.03008 — arXiv (en), https://arxiv.org/abs/2611.03008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fde368fdd192 (Metraipolis archive dc_fde368fdd192, sha256 43b89f7a37f9cf83b889be74f155412734a1b4071cd8cfe41e0b93d28aac60d5)

BibTeX

@misc{dcfde368fdd192,
  title = {E-GenRM: Generative Reward Modeling for Open-Ended E-Commerce Shopping Agents — arXiv:2611.03008},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03008},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fde368fdd192; sha256 43b89f7a37f9cf83b889be74f155412734a1b4071cd8cfe41e0b93d28aac60d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present E-GenRM (E-commerce Generative Reward Model), a generative reward model tailored to e-commerce shopping agents. User expectations are shifting from simple product queries to open-ended shopping tasks. However, existing trajectories and reward designs remain largely bounded by current agent usage patterns and known failures, providing limited guidance for further capability improvement. These limitations call for an integrated reward modeling framework for open-ended shopping agent tasks. On the data side, E-GenRM leverages naturally occurring user behavior across the shopping app to construct diverse, long-horizon conversational trajectories beyond established usage patterns. On the modeling side, E-GenRM first learns from behavior-grounded evaluation chains through supervised fine-tuning. It is then optimized through criterion-guided reinforcement learning, which rewards correct preference judgments and evidence-supported factual claims under each criterion. Personalized hard-negative training further improves its sensitivity to user preferences reflected in shopping behavior, beyond explicit requirements. We additionally develop an active evidence retrieval extension that acquires missing e-commerce information for evaluation. On E-GenRM-Bench, E-GenRM-27B achieves 87.40\% preference accuracy, outperforming the strongest baseline by 6.97 percentage points. In a 14-day online A/B test on Taobao, a shopping agent post-trained with E-GenRM improves the effective shopping-assistance rate by 1.39 percentage points and user satisfaction by 2.33 percentage points.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.03008 — 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 2026-11-03T11:06:22.199Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).