20.500.12556/RUL-190022 Agentni sistem za priporočanje izbire jezikovnega modela Agent-based system for recommending the choice of a language model Izbira jezikovnega modela na portalu Hugging Face je lahko časovno potratna. Portal ponuja le iskanje po ključnih besedah in filtriranje po oznakah. V tem delu predstavimo rešitev AgentPick, agentni sistem, ki vrne kratek seznam predlaganih modelov in vsakega utemelji s podatki iz kataloga. Velik jezikovni model v omejeni zanki sam izbira med tremi orodji (semantično iskanje po modelnih karticah, strukturirano filtriranje po metapodatkih in vpogled v posamezno kartico) nad lokalno bazo podatkov 1.709 modelov pridobljenih iz portala Hugging Face. Na dvajsetih vprašanjih, ki pokrivajo šest vrst uporabniških zahtev, je agentni sistem AgentPick priporočila rangiral bolje od običajnega s poizvedovanjem obogatenega generiranja in od samostojnega jezikovnega modela brez dostopa do kataloga. Bolje je rangiral tudi od sistema z enim krogom (brez zanke), vendar je bila ta razlika statistično značilna le pri eni meri (nDCG@3). Choosing a language model on the Hugging Face Hub can be time-consuming. The portal offers only keyword search and filtering by tags. In this work we present AgentPick, an agent-based system that returns a short list of suggested models and justifies each one with catalogue data. Within a bounded loop, a large language model picks for itself among three tools (semantic search over model cards, structured filtering over metadata and inspection of a single card) over a local database of 1,709 models collected from the Hugging Face Hub. On twenty questions covering six types of user requests, AgentPick ranked its recommendations better than the ordinary retrieval-augmented generation and a standalone language model with no access to the catalogue. It also ranked better than a single-round system (without the loop), but the difference was statistically significant for only one metric (nDCG@3). agentni sistem s poizvedovanjem obogateno generiranje besedil obdelava naravnega jezika velik jezikovni model agentic system retrieval augmented generation natural language processing large language model true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2026-10-20 14:40:05 2026-10-20 14:40:14 2026-10-21 04:19:43 0000-00-00 00:00:00 2026 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1970-01-01 38465 Madon_Matjaz_-_Agentni_sistem_za_priporocanje_izbire_jezikovnega_modela.pdf Madon_Matjaz_-_Agentni_sistem_za_priporocanje_izbire_jezikovnega_modela.pdf 1 6BD310EEA6249D22A0BAA8ACEBB8100D ec990299f7d582416d7be29283c39f9a4e2f74f0a4f8df96dd79b1939d0673f7 3eb8d3ac-cc83-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=251004 Fakulteta za računalništvo in informatiko 0 0 0