EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated MSME Bookkeeping Using Vision-Language Models and Hierarchical Multi-Agent Systems

La Ode Muhammad Yudhy Prayitno, La Ode Muhammad Golok Jaya, Asa Hari Wibowo

RIGGS: Journal of Artificial Intelligence and Digital Business · 26.06.2026 · 5 (2) · 10896-10912

DOI: 10.31004/riggs.v5i2.10269 ↗

Kurz gefasst

Fachartikel in der Zeitschrift RIGGS: Journal of Artificial Intelligence and Digital Business, online erschienen am 26.06.2026. Verfasst von La Ode Muhammad Yudhy Prayitno und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a bookkeeping automation system for micro, small, and medium enterprises (MSMEs) that converts receipt photographs into structured ledger entries without manual data transcription. Receipt-based automation is difficult because document layouts vary widely across retailers, image quality in real-world capture conditions is unreliable, and writing extracted data into a spreadsheet accounting system requires coordinated multi-step execution that a single model cannot handle end to end. The system fine-tunes Qwen 3.5-4B with Low-Rank Adaptation (LoRA) on a 1,000-image annotated receipt corpus and couples the extraction model to a LangGraph-based hierarchical multi-agent architecture whose agents access SQLite and Google Sheets through standardized Model Context Protocol (MCP) tool endpoints. When evaluated on 100 unseen test images, the fine-tuned model, configured at LoRA rank 32 and epoch 3, yields a 94.58% Digit Accuracy and an ANLS* score of 93.99 while maintaining 100% JSON validity, representing a 43.71-point and 17.09-point improvement in KIEVal Group F1 and KIEVal Entity F1, respectively, over the untuned Qwen 3.5-4B baseline and outperforming all four zero-shot baselines across every metric. Beyond individual model capabilities, the multi-agent framework, served through vLLM and exposed via a cross-platform mobile client, successfully satisfies all 22 behavioral test cases covering single-agent tool routing, cross-agent orchestration, human-in-the-loop confirmation, and input-output guardrail enforcement, demonstrating a deployable end-to-end pipeline from receipt capture to ledger update.

Zitieren

APA

Prayitno, L. O. M. Y., Jaya, L. O. M. G., & Wibowo, A. H. (2026). Automated MSME Bookkeeping Using Vision-Language Models and Hierarchical Multi-Agent Systems. RIGGS: Journal of Artificial Intelligence and Digital Business, 5(2), 10896-10912. https://doi.org/10.31004/riggs.v5i2.10269

Vancouver

Prayitno LOMY, Jaya LOMG, Wibowo AH. Automated MSME Bookkeeping Using Vision-Language Models and Hierarchical Multi-Agent Systems. RIGGS: Journal of Artificial Intelligence and Digital Business. 2026;5(2):10896-10912. doi:10.31004/riggs.v5i2.10269

BibTeX
@article{Prayitno2026,
  author = {Prayitno, La Ode Muhammad Yudhy and Jaya, La Ode Muhammad Golok and Wibowo, Asa Hari},
  title = {Automated MSME Bookkeeping Using Vision-Language Models and Hierarchical Multi-Agent Systems},
  journal = {RIGGS: Journal of Artificial Intelligence and Digital Business},
  year = {2026},
  volume = {5},
  number = {2},
  pages = {10896--10912},
  doi = {10.31004/riggs.v5i2.10269}
}
Kostenlos starten →