Metraipolis › archive › dc_dcb07b4635af

PMRecBench: A Benchmark for Personalization in Recommendation Agents under Multimodal Queries — arXiv:2611.06349

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06349
License (as archived): CC0-1.0
Archived: 2026-11-05T18:29:21.687Z
SHA-256 of the archived text: e579d16935c589ff8abb0d8bd957851b595546ad6f5a69c6f02881f84cbc3bf1
Stable URL of this page: https://metraipolis.com/documento/dc_dcb07b4635af

How to cite

PMRecBench: A Benchmark for Personalization in Recommendation Agents under Multimodal Queries — arXiv:2611.06349 — arXiv (en), https://arxiv.org/abs/2611.06349 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcb07b4635af (Metraipolis archive dc_dcb07b4635af, sha256 e579d16935c589ff8abb0d8bd957851b595546ad6f5a69c6f02881f84cbc3bf1)

BibTeX

@misc{dcdcb07b4635af,
  title = {PMRecBench: A Benchmark for Personalization in Recommendation Agents under Multimodal Queries — arXiv:2611.06349},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06349},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcb07b4635af; sha256 e579d16935c589ff8abb0d8bd957851b595546ad6f5a69c6f02881f84cbc3bf1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06349. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

On Web platforms for shopping and entertainment, recommendation agents under multimodal queries aim to deliver personalized recommendations that satisfy users' visually specified requirements and reflect preferences inferred from user histories. However, existing personalized recommendation benchmarks use text-only queries, while multimodal ones assess query matching without evaluating personalization based on real user histories. We introduce the Personalized Multimodal Recommendation Benchmark (PMRecBench), the first benchmark to evaluate the personalization of recommendation agents under multimodal queries. It pairs 510 quality-controlled image-text queries across clothing and movies with the corresponding users' real histories. PMRecBench features two key designs: (1) queries derived from consistent behavioral patterns in real user records, with reference images and targets linked to actual interactions; and (2) challenging diagnostic pools with candidate items rated highly by the user but violating requirements, and items satisfying requirements but never rated highly, testing requirement understanding and preference following, respectively. Extensive experiments on diagnostic pools reveal a personalization imbalance in recommendation agents: relative to personalization signals alone, adding multimodal queries weakens preference following, even though the additional information about query requirements improves overall ranking performance. Further analysis links this decline in preference following to image interpretation, where agents can prioritize resemblance to reference images over evidence from user histories, and stronger commercial backbones alone fail to resolve this imbalance. This personalization imbalance highlights a central challenge for recommendation agents: improving ranking performance while preserving preference following when responding to multimodal user queries

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/2611.06349 — 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 2026-11-05T18:19:33.957Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).