Metraipolis › archive › dc_506a33a1e710

Federated Recommender Agents — arXiv:2610.39289

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39289
License (as archived)
CC0-1.0
Archived
2026-11-01T02:39:57.924Z
SHA-256 of the archived text
9f8770ac8c0319bfbc1444937d202981d101e9e8594dbf081a5364a0e6b0e29c
Stable URL of this page
https://metraipolis.com/documento/dc_506a33a1e710

How to cite

Federated Recommender Agents — arXiv:2610.39289 — arXiv (en), https://arxiv.org/abs/2610.39289 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_506a33a1e710 (Metraipolis archive dc_506a33a1e710, sha256 9f8770ac8c0319bfbc1444937d202981d101e9e8594dbf081a5364a0e6b0e29c)
BibTeX
@misc{dc506a33a1e710,
  title = {Federated Recommender Agents — arXiv:2610.39289},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39289},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_506a33a1e710; sha256 9f8770ac8c0319bfbc1444937d202981d101e9e8594dbf081a5364a0e6b0e29c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39289. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-powered recommender agents use reasoning and memory for personalization, but centralized access to user information raises privacy concerns, while isolated agents cannot learn from others' experiences. We formulate Federated Recommender Agents, a setting where local agents collaborate through natural-language knowledge while keeping interaction histories and personal memories local. We propose FedRecAgent, which enables this collaboration without updating LLM parameters. Its central challenge is determining which reasoning to integrate, since similar behavioral contexts can lead to different choices. FedRecAgent represents local experiences as Condition-Transition-Reasoning (C-T-R) units and hierarchically integrates reasoning by condition and transition. Within this structure, it consolidates related explanations and discriminates reasoning across alternative transitions. Each client maintains semantic and decision memories to capture preferences and conditional choice tendencies, guiding the retrieval and selection of shared reasoning for recommendation. Experiments across three domains under dense and sparse settings demonstrate improved recommendation performance over federated and LLM-based baselines, while ablations support the contributions of personalized memories and structured reasoning integration.

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/2610.39289 — 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 2026-11-01T02:16:28.223Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).