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

• URL: http://arxiv.org/abs/2605.17159v1
• Date: Sat, 16 May 2026 21:18:39 GMT
• Title: MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop
• Abstract summary: MADP is a multi-agent architecture that combines deep learning-based classification and parsing with large language model extraction.<n>Production deployment on 955 real-world documents processed through January 2026 achieves a 97.0% full-pipeline automation rate.<n>Our hybrid AI+HITL approach reduces CO2 emissions by 69%, energy consumption by 69%, and water usage by 63% compared to traditional manual processing.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam? [90.39633603556767]
  Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested.<n>To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE)<n>We benchmark 7 frontier LLMs and observe stark limitations: single-turn models score a maximum of 36.6%.<n>A stronger agentic system with execution feedback, iterative repair, and broader Office automation access reaches 68.8%, but remains below the 95.5% community-reference score used as a scoring sanity check.
  arXiv  Detail & Related papers  (2026-06-09T14:59:14Z)
• OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation [57.505743202759646]
  OccuBench is a benchmark covering 100 real-world professional task scenarios across 10 industry categories and 65 specialized domains.<n>Our multi-agent synthesis pipeline automatically produces evaluation instances with guaranteed solvability, calibrated difficulty, and document-grounded diversity.
  arXiv  Detail & Related papers  (2026-04-13T00:27:32Z)
• ReqFusion: A Multi-Provider Framework for Automated PEGS Analysis Across Software Domains [0.45880283710344066]
  ReqFusion is an AI-enhanced system that automates the extraction, classification, and analysis of software requirements.<n>The architecture integrates OpenAI GPT, Anthropic Claude, and Groq models to extract functional and non-functional requirements.
  arXiv  Detail & Related papers  (2026-03-24T17:45:40Z)
• An Industrial-Scale Retrieval-Augmented Generation Framework for Requirements Engineering: Empirical Evaluation with Automotive Manufacturing Data [0.5156484100374058]
  Retrieval-augmented generation (RAG) shows promise for knowledge-intensive tasks, but no prior work has evaluated RAG on authentic industrial RE.<n>This paper presents a comprehensive empirical evaluation of RAG for industrial requirements engineering automation using authentic automotive manufacturing documentation.<n>RAG achieves 98.2% extraction accuracy with complete traceability, outperforming baselines by 24.4% and 19.6%, respectively.
  arXiv  Detail & Related papers  (2026-03-20T22:05:08Z)
• Dynamic Template Selection for Output Token Generation Optimization: MLP-Based and Transformer Approaches [0.0]
  Dynamic template selection achieves significant cost reductions without compromising response quality.<n>This work contributes several key elements: formal problem formulation with theoretical grounding in machine learning, four algorithms with corresponding complexity analyses, and extensive empirical validation across production systems.
  arXiv  Detail & Related papers  (2025-11-17T21:00:22Z)
• Agentic AI Sustainability Assessment for Supply Chain Document Insights [0.0]
  This paper presents a comprehensive sustainability assessment framework for document intelligence within supply chain operations centered on agentic artificial intelligence (AI)<n>We address the dual objective of improving automation efficiency while providing measurable environmental performance in document-intensive paper extraction.<n>We show that AI-assisted HITL and agentic AI scenarios achieve reductions of up to 7 in energy consumption, 90-97% in carbon dioxide emissions, and 89-98% in water usage compared to manual processes.
  arXiv  Detail & Related papers  (2025-11-10T13:38:08Z)
• Intelligent Reservoir Decision Support: An Integrated Framework Combining Large Language Models, Advanced Prompt Engineering, and Multimodal Data Fusion for Real-Time Petroleum Operations [0.0]
  This study presents a novel integrated framework combining state-of-the-art large language models with advanced prompt engineering techniques and multimodal data fusion for comprehensive reservoir analysis.<n>The framework implements domain-specific retrieval-augmented generation (RAG) with over 50,000 petroleum engineering documents, chain-of-thought reasoning, and few-shot learning for rapid field adaptation.<n>The system achieves sub-second response times while maintaining 96.2% safety reliability with no high-risk incidents during evaluation.
  arXiv  Detail & Related papers  (2025-09-14T18:13:27Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark [62.58869921806019]
  We propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset. We design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline.
  arXiv  Detail & Related papers  (2024-11-23T08:06:06Z)
• A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look [52.114284476700874]
  This paper reports on the results of a large-scale evaluation (the TREC 2024 RAG Track) where four different relevance assessment approaches were deployed. We find that automatically generated UMBRELA judgments can replace fully manual judgments to accurately capture run-level effectiveness. Surprisingly, we find that LLM assistance does not appear to increase correlation with fully manual assessments, suggesting that costs associated with human-in-the-loop processes do not bring obvious tangible benefits.
  arXiv  Detail & Related papers  (2024-11-13T01:12:35Z)
• Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs [54.05511925104712]
  We propose a simple, effective, and data-efficient method called Step-DPO. Step-DPO treats individual reasoning steps as units for preference optimization rather than evaluating answers holistically. Our findings demonstrate that as few as 10K preference data pairs and fewer than 500 Step-DPO training steps can yield a nearly 3% gain in accuracy on MATH for models with over 70B parameters.
  arXiv  Detail & Related papers  (2024-06-26T17:43:06Z)
• Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web [69.6913064185993]
  Language model agents (LMA) emerged as a promising paradigm on muti-step decision making tasks.<n>Despite the promise, their performance on real-world applications is still underexplored.<n>We show that while existing LMAs achieve 94.0% average success rate on base tasks, their performance degrades to 24.9% success rate on compositional tasks.
  arXiv  Detail & Related papers  (2023-11-30T17:50:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.