Metraipolis › archive › dc_f38ed7baa8ca

CARA: Cognitive Adaptive Recommendation Agent — arXiv:2608.16919

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16919
License (as archived)
CC0-1.0
Archived
2026-10-18T14:29:04.333Z
SHA-256 of the archived text
170f6168ca2eab1a3f8e02620587b704da7b7837aa324256618140b2cd4491de
Stable URL of this page
https://metraipolis.com/documento/dc_f38ed7baa8ca

How to cite

CARA: Cognitive Adaptive Recommendation Agent — arXiv:2608.16919 — arXiv (en), https://arxiv.org/abs/2608.16919 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f38ed7baa8ca (Metraipolis archive dc_f38ed7baa8ca, sha256 170f6168ca2eab1a3f8e02620587b704da7b7837aa324256618140b2cd4491de)
BibTeX
@misc{dcf38ed7baa8ca,
  title = {CARA: Cognitive Adaptive Recommendation Agent — arXiv:2608.16919},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16919},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f38ed7baa8ca; sha256 170f6168ca2eab1a3f8e02620587b704da7b7837aa324256618140b2cd4491de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16919. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in large language models and agent-based recommendation frameworks have introduced new opportunities for more flexible and context-aware recommendation. However, existing methods still largely rely on semantic matching, end-to-end generation, or loosely structured agent workflows, without explicitly modeling how user preferences are processed and translated into final decisions. To address this limitation, we propose CARA, a cognitively inspired recommendation framework that formulates recommendation as a structured decision-making process. The core intuition of CARA is that user decisions are jointly shaped by two complementary mechanisms: intuitive affective preference and deliberate rational evaluation. Accordingly, CARA organizes recommendation into two coordinated stages: candidate filtering, which narrows the search space based on coarse-grained preference constraints, and dual-perspective decision modeling, which captures recommendation decisions through affective and rational judgment. We further introduce a boundary-aware KTO strategy that prioritizes instructions the model can solve occasionally but not consistently, thereby increasing the density of informative preference signals. Extensive experiments on three Amazon Reviews domains show that CARA achieves the best performance on most evaluation metrics, with relative improvements of up to 10.15% over the baseline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16919 — 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 2026-10-18T14:27:54.352Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).