# MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop

arXiv: https://arxiv.org/abs/2605.17159 · HTML: https://mlsanity.com/paper/2605.17159/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 16 May 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink](https://mlsanity.com/paper/2204.05149/) (2022)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception](https://mlsanity.com/paper/2410.12628/) (2024)
- [Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction](https://mlsanity.com/paper/2410.21169/) (2024)
- [AI auditing: The Broken Bus on the Road to AI Accountability](https://mlsanity.com/paper/2401.14462/) (2024)
- [Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks](https://mlsanity.com/paper/2503.11517/) (2025)
- [Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks](https://mlsanity.com/paper/2501.13946/) (2025)
- [ParseBench: A Document Parsing Benchmark for AI Agents](https://mlsanity.com/paper/2604.08538/) (2026)
- [Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems](https://mlsanity.com/paper/2509.14956/) (2025)
- [Benchmarking Multi-Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost-Accuracy Tradeoffs and Production Scaling Strategies](https://mlsanity.com/paper/2603.22651/) (2026)
- [Prompt Injection Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching](https://mlsanity.com/paper/2601.13186/) (2026)
- [Memory-Augmented Agent Training for Business Document Understanding](https://mlsanity.com/paper/2412.15274/) (2024)
- [Improving OCR using internal document redundancy](https://mlsanity.com/paper/2508.14557/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Dual-Track Framework for Template-Constrained LaTeX Conversion](https://mlsanity.com/paper/2606.23107/) (2026)

## Abstract (arXiv)

Document processing automation remains a critical challenge in enterprise environments, where traditional manual approaches are labor-intensive and error-prone. We present MADP, a multi-agent architecture that addresses the challenge of automating document processing in enterprise settings by combining deep learning-based classification and parsing with large language model extraction, while maintaining accuracy through selective human validation. Our system integrates five specialized agents--Classificator, Splitter, Parser, Extraction, and Validator--with a Human-in-the-Loop (HITL) mechanism and a novel Prompt Fine Tuning with Feedback Inheritance (PFTFI) approach. The operational analysis on a production use-case scenario of 100,000 invoices per year indicates a potential reduction of Full-Time Equivalent (FTE) requirements by approximately 70%. Production deployment on 955 real-world documents processed through January 2026 achieves a 97.0% full-pipeline automation rate, with only 3% requiring non-AI fallback. Ablation evaluation on a stratified 100-document subset (5 documents per each of 20 supplier/document-type categories) demonstrates that the full MADP configuration with Human-in-the-Loop supervision attains 98.5% document-level accuracy. Additionally, we present a comprehensive sustainability analysis showing that our hybrid AI+HITL approach reduces CO2 emissions by 69%, energy consumption by 69%, and water usage by 63% compared to traditional manual processing. Benchmark comparisons of multiple LLM backends (Granite-Docling, Mistral-Small, DeepSeek-OCR) provide practical insights for deployment in production environments.