This study presents a modular, multi-agent system for the automated review of highly structured enterprise business documents using AI agents. Unlike prior solutions focused on unstructured texts or limited compliance checks, this framework leverages modern orchestration tools such as LangChain, CrewAI, TruLens, and Guidance to enable section-by-section evaluation of documents for accuracy, consistency, completeness, and clarity. Specialized agents, each responsible for discrete review criteria such as template compliance or factual correctness, operate in parallel or sequence as required. Evaluation outputs are enforced to a standardized, machine-readable schema, supporting downstream analytics and auditability. Continuous monitoring and a feedback loop with human reviewers allow for iterative system improvement and bias mitigation. Quantitative evaluation demonstrates that the AI Agent-as-Judge system approaches or exceeds human performance in key areas: achieving 99% information consistency (vs. 92% for humans), halving error and bias rates, and reducing average review time from 30 to 2.5 minutes per document, with a 95% agreement rate between AI and expert human judgment. While promising for a wide range of industries, the study also discusses current limitations, including the need for human oversight in highly specialized domains and the operational cost of large-scale LLM usage. The proposed system serves as a flexible, auditable, and scalable foundation for AI-driven document quality assurance in the enterprise context.

Automating table extraction (TE) from business documents is critical for industrial workflows but remains challenging due to sparse annotations and error-prone multi-stage pipelines. While semi-supervised learning (SSL) can leverage unlabeled data, existing methods rely on confidence scores that poorly reflect extraction quality. We propose QUEST, a Quality-aware Semi-supervised Table extraction framework designed for business documents. QUEST introduces a novel quality assessment model that evaluates structural and contextual features of extracted tables, trained to predict F1 scores instead of relying on confidence metrics. This quality-aware approach guides pseudo-label selection during iterative SSL training, while diversity measures (DPP, Vendi score, IntDiv) mitigate confirmation bias. Experiments on a proprietary business dataset (1000 annotated + 10000 unannotated documents) show QUEST improves F1 from 64% to 74% and reduces empty predictions by 45% (from 12% to 6.5%). On the DocILE benchmark (600 annotated + 20000 unannotated documents), QUEST achieves a 50% F1 score (up from 42%) and reduces empty predictions by 19% (from 27% to 22%). The framework's interpretable quality assessments and robustness to annotation scarcity make it particularly suited for business documents, where structural consistency and data completeness are paramount.

Businesses heavily rely on data sourced from various channels like news articles, financial reports, and consumer reviews to drive their operations, enabling informed decision-making and identifying opportunities. However, traditional manual methods for data extraction are often time-consuming and resource-intensive, prompting the adoption of digital transformation initiatives to enhance efficiency. Yet, concerns persist regarding the sustainability of such initiatives and their alignment with the United Nations (UN)'s Sustainable Development Goals (SDGs). This research aims to explore the integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) as a sustainable solution for Information Extraction (IE) and processing. The research methodology involves reviewing existing solutions for business decision-making, noting that many systems require training new machine learning models, which are resource-intensive and have significant environmental impacts. Instead, we propose a sustainable business solution using pre-existing LLMs that can work with diverse datasets. We link domain-specific datasets to tailor LLMs to company needs and employ a Multi-Agent architecture to divide tasks such as information retrieval, enrichment, and classification among specialized agents. This approach optimizes the extraction process and improves overall efficiency. Through the utilization of these technologies, businesses can optimize resource utilization, improve decision-making processes, and contribute to sustainable development goals, thereby fostering environmental responsibility within the corporate sector.

Traditional enterprises face significant challenges in processing business documents, where tasks like extracting transport references from invoices remain largely manual despite their crucial role in logistics operations. While Large Language Models offer potential automation, their direct application to specialized business domains often yields unsatisfactory results. We introduce Matrix (Memory-Augmented agent Training through Reasoning and Iterative eXploration), a novel paradigm that enables LLM agents to progressively build domain expertise through experience-driven memory refinement and iterative learning. To validate this approach, we collaborate with one of the world's largest logistics companies to create a dataset of Universal Business Language format invoice documents, focusing on the task of transport reference extraction. Experiments demonstrate that Matrix outperforms prompting a single LLM by 30.3%, vanilla LLM agent by 35.2%. We further analyze the metrics of the optimized systems and observe that the agent system requires less API calls, fewer costs and can analyze longer documents on average. Our methods establish a new approach to transform general-purpose LLMs into specialized business tools through systematic memory enhancement in document processing tasks.

However, to this day, physical paper documents still play an important role in business operations, as they are a key means of communication related to transactions both within and between organizations [120]. The processing of such documents is an essential yet time-consuming task that offers a high potential for automation due to the high workload involved as well as the critical nature of information transfer between different information systems [19, 130]. At the same time, it can be observed that the ongoing digital transformation of business operations is leading to an increase in the digital processing of documents. This trend reinforces the need - but also the potential - for automated document processing, as more and more documents are available in digital form [113].

In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting information using a specific, predefined set of keys. Unlike most existing datasets and benchmarks, our focus is on discovering key-value pairs (KVPs) without relying on predefined keys, navigating through an array of diverse templates and complex layouts. This task presents unique challenges, primarily due to the absence of comprehensive datasets and benchmarks tailored for non-predetermined KVP extraction. To address this gap, we introduce KVP10k , a new dataset and benchmark specifically designed for KVP extraction. The dataset contains 10707 richly annotated images. In our benchmark, we also introduce a new challenging task that combines elements of KIE as well as KVP in a single task. KVP10k sets itself apart with its extensive diversity in data and richly detailed annotations, paving the way for advancements in the field of information extraction from complex business documents.

Transformer-based Language Models are widely used in Natural Language Processing related tasks. Thanks to their pre-training, they have been successfully adapted to Information Extraction in business documents. However, most pre-training tasks proposed in the literature for business documents are too generic and not sufficient to learn more complex structures. In this paper, we use LayoutLM, a language model pre-trained on a collection of business documents, and introduce two new pre-training tasks that further improve its capacity to extract relevant information. The first is aimed at better understanding the complex layout of documents, and the second focuses on numeric values and their order of magnitude. These tasks force the model to learn better-contextualized representations of the scanned documents. We further introduce a new post-processing algorithm to decode BIESO tags in Information Extraction that performs better with complex entities. Our method significantly improves extraction performance on both public (from 93.88 to 95.50 F1 score) and private (from 84.35 to 84.84 F1 score) datasets composed of expense receipts, invoices, and purchase orders.

This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k synthetically generated documents, and nearly 1M unlabeled documents for unsupervised pre-training. The dataset has been built with knowledge of domain-and task-specific aspects, resulting in the following key features: (i) annotations in 55 classes, which surpasses the granularity of previously published key information extraction datasets by a large margin; (ii) Line Item Recognition represents a highly practical information extraction task, where key information has to be assigned to items in a table; (iii) documents come from numerous layouts and the test set includes zero-and few-shot cases as well as layouts commonly seen in the training set. The benchmark comes with several baselines, including RoBERTa, LayoutLMv3 and DETRbased Table Transformer; applied to both tasks of the DocILE benchmark, with results shared in this paper, offering a quick starting point for future work. The dataset, baselines and supplementary material are available at https://github.com/rossumai/docile. Keywords: Document AI Information Extraction Line Item Recognition Business Documents Intelligent Document Processing

Is ChatGPT the beginning of the Star Trek vision: We'll just tell the computer what we want it to do? The short answer is: Not right now, and probably not any time soon. That's because the types of coding problems at which ChatGPT seems to excel are common ones. If you ask it to do something that's been done a ton of times before, then sure, it'll do a very good job. These have been coded a bajillion times before, and they're all online. OpenAI trained its models on all that existing code.

Business documents come in a variety of structures, formats and information needs which makes information extraction a challenging task. Due to these variations, having a document generic model which can work well across all types of documents and for all the use cases seems far-fetched. For document-specific models, we would need customized document-specific labels. We introduce DoSA (Document Specific Automated Annotations), which helps annotators in generating initial annotations automatically using our novel bootstrap approach by leveraging document generic datasets and models. These initial annotations can further be reviewed by a human for correctness. An initial document-specific model can be trained and its inference can be used as feedback for generating more automated annotations. These automated annotations can be reviewed by human-in-the-loop for the correctness and a new improved model can be trained using the current model as pre-trained model before going for the next iteration. In this paper, our scope is limited to Form like documents due to limited availability of generic annotated datasets, but this idea can be extended to a variety of other documents as more datasets are built. An open-source ready-to-use implementation is made available on GitHub https://github.com/neeleshkshukla/DoSA.