Metraipolis › archive › dc_991cfe5cdca7

AtomRec: Evolving Atomic Memory for Agentic Recommendation — arXiv:2609.04882

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04882
License (as archived)
CC0-1.0
Archived
2026-10-16T23:30:39.070Z
SHA-256 of the archived text
4f7ddc74172e8b40443565d8ae63743e8d18167a1bd720fe6cd065389f357a1a
Stable URL of this page
https://metraipolis.com/documento/dc_991cfe5cdca7

How to cite

AtomRec: Evolving Atomic Memory for Agentic Recommendation — arXiv:2609.04882 — arXiv (en), https://arxiv.org/abs/2609.04882 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_991cfe5cdca7 (Metraipolis archive dc_991cfe5cdca7, sha256 4f7ddc74172e8b40443565d8ae63743e8d18167a1bd720fe6cd065389f357a1a)
BibTeX
@misc{dc991cfe5cdca7,
  title = {AtomRec: Evolving Atomic Memory for Agentic Recommendation — arXiv:2609.04882},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04882},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_991cfe5cdca7; sha256 4f7ddc74172e8b40443565d8ae63743e8d18167a1bd720fe6cd065389f357a1a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04882. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic recommender systems use large language models to maintain semantic memory and support evidence-aware recommendation. However, existing memory mechanisms often compress user and item information into coarse summaries and connect them with scalar collaborative links, making it difficult to preserve fine-grained preference stages or retrieve interpretable evidence as user interests evolve. We propose \textsc{AtomRec}, an agentic recommender with evolving atomic collaborative memory. \textsc{AtomRec} represents user and item memories as structured atomic units, builds semantic links across related memories, and evolves related historical fields when new interactions arrive. During recommendation, it retrieves linked memories as multi-hop evidence paths rather than isolated neighbor summaries, allowing collaborative signals to support grounded ranking. Experiments on four public benchmarks show that \textsc{AtomRec} consistently outperforms state-of-the-art agentic and memory-augmented baselines, with around 8.5\% average relative improvement across metrics.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.04882 — 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 2026-10-16T23:15:50.037Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).