Metraipolis › archive › dc_7bc040235b16

Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It — arXiv:2610.03195

Source
arXiv
Original
https://arxiv.org/abs/2610.03195
License (as archived)
CC0-1.0
Archived
2026-10-05T22:51:45.302Z
SHA-256 of the archived text
7b259cc51e141dffc4e12c84bf88b483beb793d92da7904d1abf8284d290569a
Stable URL of this page
https://metraipolis.com/documento/dc_7bc040235b16

How to cite

Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It — arXiv:2610.03195 — arXiv, https://arxiv.org/abs/2610.03195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bc040235b16 (Metraipolis archive dc_7bc040235b16, sha256 7b259cc51e141dffc4e12c84bf88b483beb793d92da7904d1abf8284d290569a)
BibTeX
@misc{dc7bc040235b16,
  title = {Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It — arXiv:2610.03195},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03195},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bc040235b16; sha256 7b259cc51e141dffc4e12c84bf88b483beb793d92da7904d1abf8284d290569a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (the sites or services they come from) shapes what users receive and which sources are selected. We study source preference in end-to-end search with 12 agent models across three domains. Comparing items from different sources that satisfy the same requirements at the same position, we find that each model prefers some sources and avoids others in every domain, largely agreeing on which. This preference can outweigh how well items satisfy the request: an item satisfying one requirement fewer is selected about two-thirds of the time when it comes from a preferred source and the better one from a dispreferred source, but almost never in the reverse case. The information identifying an item's source affects selection by itself: hiding it weakens the preference, and relabeling an item with a preferred source raises its selection rate. We test two routes to this preference: training that rewards better items can make a source a shortcut for requirement satisfaction, and missing information can trigger preconceptions about the source. Supplying missing information or a prompt countering these preconceptions reduces source preference.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.03195 — 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 2026-10-05T22:46:10.579Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).