Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Artificial Intelligence and Digital Business
La Ode Muhammad Yudhy Prayitno
Halu Oleo University
Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
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 Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.10269

Abstract

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.
Co-Authors Asa Hari Wibowo La Ode Muhammad Golok Jaya