Institutional Repository of Vilnius University
Daugiaagentė sistema, naudojanti didelės kalbos modelius verslo procesams automatizuoti /
Abstract
dc:descriptionInvoice processing is an expensive part of accounting: some Lithuanian companies pay up to 0,30 EUR for each invoice to be processed, while others send the documents to „Microsoft Document Intelligence“ or „Google Document AI“, thus letting the data out of company boundaries. This paper analyses a third variant: can a locally‑hosted open‑source model replace these solutions. Experiment uses 33 real invoices to test seven local models (from 2 billion parameter „Gemma 4 E2B“ till 27 billion parameter „Qwen 3.6 27B“) and two cloud models („GPT‑5.4‑nano“, „GPT‑5.5“) in five scenarios, including a multi‑agent system with extractor, judge, formatter agents. The best local model („Mistral Devstral Small 2 2512“) with „Tesseract“ OCR help achieves the same F1 score as „GPT‑5.5“ (≈0,90), while using only half of the output tokens. Smaller models’ accuracy is increased by 0,16‑0,18 adding OCR, reasoning add no additional value, and parallel processing increases throughput up to 60 % without accuracy cost. Total cost of the experiment was ≈4.63 EUR, 20 to 540 times cheaper than the same workload would have been on cloud services.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Džiaugys, Nojus,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308336747&prefLang=en_US