In this work, we propose Few Shot Domain Adapting Graph (FS-DAG), a scalable and efficient model architecture for visually rich document understanding (VRDU) in few-shot settings. FS-DAG leverages domain-specific and language/vision specific backbones within a modular framework to adapt to diverse document types with minimal data. The model is robust to practical challenges such as handling OCR errors, misspellings, and domain shifts, which are critical in real-world deployments. FS-DAG is highly performant with less than 90M parameters, making it well-suited for complex real-world applications for Information Extraction (IE) tasks where computational resources are limited. We demonstrate FS-DAG's capability through extensive experiments for information extraction task, showing significant improvements in convergence speed and performance compared to state-of-the-art methods. Additionally, this work highlights the ongoing progress in developing smaller, more efficient models that do not compromise on performance. Code : https://github.com/oracle-samples/fs-dag

We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse real-world scenarios, including academic papers, textbooks, e-books, and multilingual documents. Each document has been processed using state-of-the-art Vision-Language Models (VLMs) and manually annotated with quality scores using a 4-level scoring system (1: Excellent, 2: Good, 3: Fair, 4: Poor). The dataset includes detailed source information, annotation guidelines, and representative cases across various difficulty levels. OCR-Quality addresses the critical need for reliable OCR quality assessment in real-world applications and provides a valuable benchmark for training and evaluating OCR verification systems. The dataset is publicly available at https://huggingface.co/datasets/Aslan-mingye/OCR-Quality .

Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse layouts. We introduce layoutRL, an end-to-end reinforcement learning framework that trains models to be explicitly layout-aware by optimizing a composite reward of normalized edit distance, paragraph count accuracy, and reading order preservation. Leveraging our newly released dataset, Infinity-Doc-55K, which combines 55K high-fidelity synthetic scanned document parsing data with expert-filtered real-world documents, we instantiate layoutRL in a vision-language-model-based parser called Infinity-Parser. Evaluated on English and Chinese benchmarks for OCR, table and formula extraction, and reading order detection, Infinity-Parser achieves new state-of-the-art performance in both accuracy and structural fidelity, outpacing specialist pipelines and general-purpose vision-language models. We will publicly release our code and dataset to accelerate progress in robust document understanding.

Accurate information retrieval (IR) is critical in the financial domain, where investors must identify relevant information from large collections of documents. Traditional IR methods -- whether sparse or dense -- often fall short in retrieval accuracy, as it requires not only capturing semantic similarity but also performing fine-grained reasoning over document structure and domain-specific knowledge. Recent advances in large language models (LLMs) have opened up new opportunities for retrieval with multi-step reasoning, where the model ranks passages through iterative reasoning about which information is most relevant to a given query. However, there exists no benchmark to evaluate such capabilities in the financial domain. To address this gap, we introduce FinAgentBench, the first large-scale benchmark for evaluating retrieval with multi-step reasoning in finance -- a setting we term agentic retrieval. The benchmark consists of 26K expert-annotated examples on S&P-500 listed firms and assesses whether LLM agents can (1) identify the most relevant document type among candidates, and (2) pinpoint the key passage within the selected document. Our evaluation framework explicitly separates these two reasoning steps to address context limitations. This design enables to provide a quantitative basis for understanding retrieval-centric LLM behavior in finance. We evaluate a suite of state-of-the-art models and further demonstrated how targeted fine-tuning can significantly improve agentic retrieval performance. Our benchmark provides a foundation for studying retrieval-centric LLM behavior in complex, domain-specific tasks for finance.

Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency. However, these documents are often lengthy, structurally diverse, and multimodal, comprising dense text, structured tables, complex figures, and layout-dependent semantics. Existing AI systems often struggle to perform reliable document-level reasoning in such settings, and no dedicated benchmark currently exists in ESG domain. To fill the gap, we introduce \textbf{MMESGBench}, a first-of-its-kind benchmark dataset targeted to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents. This dataset is constructed via a human-AI collaborative, multi-stage pipeline. First, a multimodal LLM generates candidate question-answer (QA) pairs by jointly interpreting rich textual, tabular, and visual information from layout-aware document pages. Second, an LLM verifies the semantic accuracy, completeness, and reasoning complexity of each QA pair. This automated process is followed by an expert-in-the-loop validation, where domain specialists validate and calibrate QA pairs to ensure quality, relevance, and diversity. MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories. Questions are categorized as single-page, cross-page, or unanswerable, with each accompanied by fine-grained multimodal evidence. Initial experiments validate that multimodal and retrieval-augmented models substantially outperform text-only baselines, particularly on visually grounded and cross-page tasks. MMESGBench is publicly available as an open-source dataset at https://github.com/Zhanglei1103/MMESGBench.

Retrieval-Augmented Generation (RAG) systems using Multimodal Large Language Models (MLLMs) show great promise for complex document understanding, yet their development is critically hampered by inadequate evaluation. Current benchmarks often focus on specific part of document RAG system and use synthetic data with incomplete ground truth and evidence labels, therefore failing to reflect real-world bottlenecks and challenges. To overcome these limitations, we introduce Double-Bench: a new large-scale, multilingual, and multimodal evaluation system that is able to produce fine-grained assessment to each component within document RAG systems. It comprises 3,276 documents (72,880 pages) and 5,168 single- and multi-hop queries across 6 languages and 4 document types with streamlined dynamic update support for potential data contamination issues. Queries are grounded in exhaustively scanned evidence pages and verified by human experts to ensure maximum quality and completeness. Our comprehensive experiments across 9 state-of-the-art embedding models, 4 MLLMs and 4 end-to-end document RAG frameworks demonstrate the gap between text and visual embedding models is narrowing, highlighting the need in building stronger document retrieval models. Our findings also reveal the over-confidence dilemma within current document RAG frameworks that tend to provide answer even without evidence support. We hope our fully open-source Double-Bench provide a rigorous foundation for future research in advanced document RAG systems. We plan to retrieve timely corpus and release new benchmarks on an annual basis.

Many document types use intrinsic, convention-driven structures that serve to encode precise and structured information, such as the conventions governing engineering drawings. However, state-of-the-art approaches treat document recognition as a mere computer vision problem, neglecting these underlying document-type-specific structural properties, making them dependent on sub-optimal heuristic post-processing and rendering many less frequent or more complicated document types inaccessible to modern document recognition. We suggest a novel perspective that frames document recognition as a transcription task from a document to a record. This implies a natural grouping of documents based on the intrinsic structure inherent in their transcription, where related document types can be treated (and learned) similarly. We propose a method to design structure-specific inductive biases for the underlying machine-learned end-to-end document recognition systems, and a respective base transformer architecture that we successfully adapt to different structures. We demonstrate the effectiveness of the so-found inductive biases in extensive experiments with progressively complex record structures from monophonic sheet music, shape drawings, and simplified engineering drawings. By integrating an inductive bias for unrestricted graph structures, we train the first-ever successful end-to-end model to transcribe engineering drawings to their inherently interlinked information. Our approach is relevant to inform the design of document recognition systems for document types that are less well understood than standard OCR, OMR, etc., and serves as a guide to unify the design of future document foundation models.

Extracting alphanumeric data from form-like documents such as invoices, purchase orders, bills, and financial documents is often performed via vision (OCR) and learning algorithms or monolithic pipelines with limited potential for systemic improvements. We propose an agen-tic AI system that leverages Large Language Model (LLM) agents and a reinforcement learning (RL) driver agent to automate consistent, self-improving extraction under LLM inference uncertainty. Our work highlights the limitations of monolithic LLM-based extraction and introduces a modular, multi-agent framework with task-specific prompts and an RL policy of rewards and penalties to guide a meta-prompting agent to learn from past errors and improve prompt-based actor agents. This self-corrective adaptive system handles diverse documents, file formats, layouts, and LLMs, aiming to automate accurate information extraction without the need for human intervention. Results as reported on two benchmark datasets of SOIRE, and CORD, are promising for the agen-tic AI framework.

Objective: Electronic health records (EHR) are widely available to complement administrative data-based disease surveillance and healthcare performance evaluation. Defining conditions from EHR is labour-intensive and requires extensive manual labelling of disease outcomes. This study developed an efficient strategy based on advanced large language models to identify multiple conditions from EHR clinical notes. Methods: We linked a cardiac registry cohort in 2015 with an EHR system in Alberta, Canada. We developed a pipeline that leveraged a generative large language model (LLM) to analyze, understand, and interpret EHR notes by prompts based on specific diagnosis, treatment management, and clinical guidelines. The pipeline was applied to detect acute myocardial infarction (AMI), diabetes, and hypertension. The performance was compared against clinician-validated diagnoses as the reference standard and widely adopted International Classification of Diseases (ICD) codes-based methods. Results: The study cohort accounted for 3,088 patients and 551,095 clinical notes. The prevalence was 55.4%, 27.7%, 65.9% and for AMI, diabetes, and hypertension, respectively. The performance of the LLM-based pipeline for detecting conditions varied: AMI had 88% sensitivity, 63% specificity, and 77% positive predictive value (PPV); diabetes had 91% sensitivity, 86% specificity, and 71% PPV; and hypertension had 94% sensitivity, 32% specificity, and 72% PPV. Compared with ICD codes, the LLM-based method demonstrated improved sensitivity and negative predictive value across all conditions. The monthly percentage trends from the detected cases by LLM and reference standard showed consistent patterns.

Research on using Large Language Models (LLMs) in system development is expanding, especially in automated code and test generation. While E2E testing is vital for ensuring application quality, most test generation research has focused on unit tests, with limited work on E2E test code. This study proposes a method for automatically generating E2E test code from product documentation such as manuals, FAQs, and tutorials using LLMs with tailored prompts. The two step process interprets documentation intent and produces executable test code. Experiments on a web app with six key features (e.g., authentication, profile, discussion) showed that tests generated from product documentation had high compilation success and functional coverage, outperforming those based on requirement specs and user stories. These findings highlight the potential of product documentation to improve E2E test quality and, by extension, software quality.