Document Understanding

Each year, college admissions offices face an overwhelming challenge: processing millions of high school transcripts, each with unique formats, grading systems, and layouts. This manual process creates operational bottlenecks that delay admissions decisions and consume valuable resources. We present a transformative solution through a multi-agent AI system where specialized agents collaborate to automatically process diverse transcript formats through intelligent coordination and communication. Our multi-agent architecture consists of three specialized agents-a Pattern Recognition Agent for format-specific parsing, a Semantic Analysis Agent for natural language understanding, and a Vision Intelligence Agent for multimodal document analysis-coordinated by an Orchestration Agent that manages agent communication and result reconciliation. Our key innovation lies in agent-based quality control using GPA extraction as a coordination signal, ensuring reliable agent collaboration and preventing critical information loss. When evaluated on 40 real world transcripts from high schools across 13 U.S. states, our agent system successfully processed every document, achieving 96.7% accuracy compared to expert manual review while maintaining practical processing speeds of 45 seconds per transcript. This work demonstrates how multi-agent coordination can solve complex document processing challenges, offering institutions a scalable, collaborative AI solution that preserves accuracy while dramatically reducing processing time.

Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table reasoning tasks, but the role of table representation remains under-explored. In practice, the same table content may appear in different structural formats, such as HTML, Markdown, and LaTeX, or as rendered images. However, existing evaluations often let content, format, layout, and modality vary together, making it difficult to isolate representation effects. We introduce TABVERSE, a controlled multimodal table benchmark that aligns the same table content across multiple structural formats and rendered images, with question category and difficulty tags. This design enables systematic evaluation of representation effects while holding table content fixed. We evaluate LLMs and VLMs across three tasks: Question Answering (QA), Structural Understanding Capability (SUC), and Structure Reconstruction (SR). Our results show that representation choice substantially affects table understanding. Models generally perform better with structured text than with rendered images, but the size of this gap depends on the task, model, and format. HTML is often the most robust text format, while row-sensitive structural tasks and syntactically usable LaTeX reconstruction remain challenging. These findings show that table representation is a key factor in reliable table evaluation.

Document type classification in visually rich documents remains challenging, as relevant information is distributed across textual, visual, and layout modalities. To capture this complexity, current approaches rely on diverse multimodal modeling strategies, resulting in heterogeneous architectures that complicate systematic comparison. This variability is also reflected in existing comparative studies, which often rely on heterogeneous evaluation setups, further complicating systematic comparison and making it difficult to assess progress. To address these limitations, this work provides a structured analysis of multimodal design strategies across transformer- and LLM-based architectures, combined with a controlled empirical comparison within a unified experimental framework. Specifically, four representative models (LayoutLMv3, Donut, Qwen3-VL-32B-Instruct, and Qwen3-32B) are evaluated on the RVL-CDIP benchmark to systematically analyze the contributions of text, image, and layout information for document type classification, with a particular focus on contrasting OCR-dependent and OCR-free approaches. The results show that specialized multimodal Transformers outperform LLM-based approaches on visually rich and layout-intensive documents. Image information contributes most strongly to reliable classification, while OCR-derived text provides useful but secondary support. These findings highlight that multimodal processing remains essential for documents with pronounced layout structure. Overall, the study provides a systematic basis for comparing multimodal architectures and offers practical guidance for selecting effective feature combinations and model designs for document type classification.

We introduce Office Comprehension Bench (OCB), the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension over native file formats (.docx, .xlsx, .pptx) and their variants. OCB consists of two tracks. File Fidelity Q&A tests structural and visual perception of office artifacts - tables, charts, embedded images, formulas, and app-specific elements such as headers, speaker notes, and named ranges. Domain Q&A tests expert-level reasoning grounded in real-world industry documents across 12 professional domains, with queries requiring multi-step analysis and synthesis across documents. Each reference answer is decomposed into atomic, binary-gradable claims, and an ensemble of LLM judges scores responses against each claim independently. Even the strongest frontier system in its default reasoning mode reaches only about 59.3% on Domain Q&A; increasing thinking depth within a tier does not move performance materially, while moving to a higher product tier yields modest gains. We release the dataset, evaluation tooling, judge prompt, and a public leaderboard.

We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575). The corpus comprises 20,898 pages and 499,222 text lines written by 796 writers over six decades, featuring stylistic variation, multilingual content (mostly Latin and Early New High German) as well as meta-information such as writer identity and time. We evaluate BullingerDB on text recognition and writer retrieval. TrOCR, the best performing model, achieves a CER of 9.1%. For writer retrieval, we introduce a temporal nDCG metric to assess time-aware retrieval. While temporally coherent retrieval is achievable, mAP (78.3%) scores indicate challenges due to long-term stylistic variation. With BullingerDB, we aim to establish a new benchmark for multilingual historical text recognition and temporally-aware writer analysis.

Recent work has shown that Vision-Language Models (VLMs) used for optical character recognition (OCR) can generate plausible but visually unsupported text, suggesting reliance on language priors. Comparing open-weight VLMs with traditional OCR baselines on low-resource Ancient Greek critical editions, we show that VLM errors often remain fluent even when wrong, producing plausible Greek substitutions where traditional engines produce local recognition noise. To analyze visual evidence during decoding, we introduce controlled image perturbations and token-level grounding measures based on conditional versus image-free decoding distributions. Under character-level perturbations, VLMs diverge sharply from the perturbed ground truth while traditional OCR remains comparatively faithful; however, token-level analysis shows that prior reliance is model-specific: in an OCR-specialist model, fluent lexical errors are produced with little reliance on the image, whereas general-purpose VLMs remain conditioned on the visual input even when wrong. Decode-time interventions fail to reliably restore grounding, while post-OCR language-model correction improves several systems only by repairing text after generation. Our results extend prior evidence of OCR language-prior reliance to low-resource historical documents and a broader set of models, showing that fluent output is not necessarily visually grounded and motivating interpretability-driven evaluation beyond aggregate accuracy.

This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote Brain architecture via Google Colab, utilizing Python-based local orchestrators to invoke large language model (LLM) cloud backends. The first agent, DeepTS/DeepCollector, automates the large-scale curation, extraction, and deduplication of time-series datasets. The second, DeepScribe, is an autonomous presentation analyzer that converts visually dense, mathematically complex physics lectures into structured scientific reports. Through practical systems engineering-such as granular attribute extraction (Cellular RAG), remote data inspection, and distributed concurrency controls-we demonstrate how agentic AI can overcome the context and reasoning limitations of current state-of-the-art systems to rigorously support scientific workflows. Finally, we outline a generalization of DeepTS to support deep knowledge graphs and discuss the application of this conceptual approach to high-energy physics (DeepQCD).

Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+, a multimodal extension that uses Vision-Language Models (VLMs) for end-to-end referral understanding. We evaluate fine-tuned VLMs, commercial and open-source zero-shot VLMs, and the original OCR-based pipeline on 223 clinically curated CRC urgent referral forms. We also introduce a grounding-aware evaluation framework that measures both extraction accuracy and evidence localisation. Results show a clear grounding gap in zero-shot models. Gemini 2.5 Flash achieved 92.6% Reading Accuracy but only 1.2% Strict Safety. In contrast, fine-tuned Qwen3-VL-8B achieved 96.1% Reading Accuracy and 60.6% Strict Safety, substantially improving verifiable evidence grounding. These findings show that task-specific fine-tuning is essential for reliable, auditable clinical document understanding. RAPTOR+ enables extracted referral decisions to be linked to visual evidence, supporting safer and more efficient cancer referral triage.

Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at scale. This work addresses the need for an automated system to classify scanned page images based on visual content type - text, tables, and graphics - enabling content-specific downstream processing such as Optical Character Recognition (OCR) or structured data extraction. Methods: An image classification system was developed and evaluated on a dataset of over 48,000 annotated historical page images from century-old Czech archaeological archives, refined through four successive annotation stages with domain-expert review. A Random Forest Classifier baseline was established using hand-crafted image features. Subsequently, deep learning architectures were fine-tuned and compared: Convolutional Neural Networks (EfficientNetV2, RegNetY), Vision and Document Image Transformers (ViT, DiT), and multimodal CLIP models. An 11-category label scheme was designed collaboratively with domain experts and evaluated via five-fold cross-validation. Results: The feature-based baseline achieved approximately 75% accuracy. Fine-tuned CNNs and Transformers substantially outperformed it, with RegNetY-16GF achieving 99.16% and ViT-large 99.12% Top-1 accuracy on the held-out test set. CLIP ViT-B/16 reached 99.14% with optimized text descriptions. Conclusion: Image-only models, particularly RegNetY-16GF, deliver near-perfect classification accuracy and produce consistent labels across 649,508 unlabeled archival pages with over 90% inter-model agreement. Fine-tuned CLIP, despite competitive test-set accuracy, showed under 65% agreement with image-only models on unlabeled data, making it less suitable for deployment. The final models, annotated dataset, and software are publicly available under open-source licenses.

Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models (MLLMs) have shown promising capabilities, existing benchmarks suffer from critical limitations in scale and realism, lack semantic granularity, and fail to cover diverse document types. To bridge this gap, we introduce ReceiptBench, a large-scale, human-annotated benchmark consisting of 10k diverse receipts, organizing information extraction into four hierarchical sub-tasks: (1) Basic Perception for raw text spotting, (2) Format Normalization for strictly following standardization instructions, (3) Semantic Reasoning for inferring implicit attributes from context, and (4) Structure Parsing for handling nested line items. Furthermore, we propose a two-stage training framework incorporating Metric-Aware Group Relative Policy Optimization (GRPO), which translates rigorous evaluation constraints into reinforcement learning signals to enhance structural consistency. Extensive experiments demonstrate that our method yields state-of-the-art performance, surpassing leading proprietary models on complex reasoning tasks. We release our datasets and code at https://github.com/wwwT0ri/ReceiptBench.

Manga is a culturally distinctive multimodal medium and one of the most influential forms of Japanese popular culture. As AI systems increasingly target manga understanding, OCR, and translation, Manga109 has become a foundational dataset for manga-related AI research. However, the current Manga109 dataset contains inaccurate transcriptions and coarse annotations, which do not align well with modern OCR and multimodal manga understanding tasks. In this work, we revisit the dialogue text annotations of Manga109 and identify five categories of annotation issues, including inaccurate transcriptions, missing text regions, overlapping dialogue and onomatopoeia, and under-segmented speech balloons. To address these issues, we combine OCR-based issue detection and manual revision to construct Manga109-v2026, revising approximately 29,000 dialogue annotations. Our revisions better align Manga109 with modern OCR and multimodal manga understanding systems while preserving expressive structures characteristic of manga.

Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affects the accuracy of downstream information extraction from the document, as well as the associated verification effort. In practice, OCR noise, label imbalance, instance-dependent label cardinality, and asymmetric error costs make global score thresholds brittle and hard to maintain as document formats evolve. We present RAPT, a deployment-oriented retrieval-augmented score thresholding wrapper, applied post-hoc to improve label set selection without retraining the underlying classifier. RAPT is a model-agnostic wrapper: any predictor that provides document representations for similarity search and per label confidence scores can be used, including metric learning encoders and fine-tuned transformer classifiers. For each query document, given a classifier's score vector, RAPT retrieves similar document thresholding situations (cases) and adapts the query's label set selection threshold using their outcomes. The adaptation selects the final label set by locally aggregating neighbour solutions (e.g. average label count, cutoff calibration). Evaluation compared multi-label classifiers (metric learners and transformers) combined with RAPT against global and label-wise thresholding baselines, and against few-shot LLMs. Across an industrial dataset and six public benchmarks, RAPT consistently outperformed global and label-wise static thresholding baselines. In the industrial setting, RAPT achieved its best predictive performance with metric learners, reaching 0.87 Macro-F1, while fine-tuned transformer variants on average achieved 0.775 Macro-F1, outperforming fewshot LLM baselines (K = 5) by 2x and requiring at least 115x less inference time and 13.5x less GPU memory.

Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models by conditioning their outputs on external documents. However, standard embedding-based retrievers treat naturally structured corpora, such as technical manuals, as flat collections of passages, thereby overlooking the hyperlink topology that users rely on when navigating such content. We introduce LARAG (Link-Aware RAG): a lightweight, link-aware retrieval strategy that leverages the author-defined hyperlink structure already present in HTML documentation, encoding hyperlink relations as metadata in the chunk representations and exploiting them to perform a form of graph-like retrieval of locally relevant content. In a benchmark of twenty expert-designed queries over Rulex Platform technical documentation and four prompting strategies, LARAG consistently improves answer quality, achieving the highest BERTScore F1, while retrieving fewer chunks and generating fewer tokens than a baseline RAG architecture used for comparison. These results show that directly leveraging the existing hyperlink topology of technical documentation, even without explicit graph construction or inference, enables an implicit form of graph-like retrieval that yields a more faithful and efficient RAG pipeline, providing better grounding at lower cost.

Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of visual tokens, varying rendering resolution provides a fine-grained compression knob. However, accuracy deteriorates quickly as compression increases: characters shrink below the vision encoder's effective resolution, making them indistinguishable. To address this, we propose LensVLM, an inference framework and post-training recipe that enables VLMs to scan compressed images, then selectively expand only the relevant images to their uncompressed form via learned tools. Building on Qwen3.5-9B-Base, LensVLM maintains accuracy comparable to the full-text upper bound at 4.3$\times$ effective compression and outperforms retrieval-based, text- and visual-compression baselines up to 10.1$\times$ effective compression across seven text QA benchmarks. LensVLM also generalizes to multimodal document and code understanding tasks, with the accuracy gain over baselines growing as compression increases. Our analysis validates this approach: training makes visual compression robust to rendering choices, and as compression grows the model increasingly relies on expanded content rather than unreliable visual reading. The analysis also yields practical tool-choice guidance: text expansion is preferable for rendered text, while high-resolution image expansion suits native documents whose layout cues carry task-relevant information.

Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token contexts end-to-end, but they suffer from high token consumption and attention dilution. In parallel, specialized LTU agents often sacrifice fidelity through task-agnostic abstractions like graph construction or indexing. We identify a key insight for LTU: query-relevant information is typically sparse relative to the full document, so effective reasoning should rely on a query-sufficient subset rather than the entire context. To address this, we propose SCOUT, a new paradigm for LTU that shifts from passive processing to active information foraging. It treats the document as an explorable environment and answers from a compact, provenance-grounded epistemic state. Guided by state-level gap diagnosis, SCOUT adaptively alternates between coarse-to-fine exploration and anchored state updates that progressively contract its epistemic state toward query sufficiency. Experiments show that SCOUT matches state-of-the-art proprietary models while reducing token consumption by up to 8x. Moreover, SCOUT remains stable as context length scales, substantially alleviating the practical cost-performance trade-off.

Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications remains underexplored, as existing benchmarks adopt task scopes misaligned with practical applications and assume homogeneous acquisition conditions. To address this gap, we introduce CC-OCR V2, a comprehensive and challenging OCR benchmark tailored to real-world document processing. CC-OCR V2 focuses on practical enterprise document processing tasks and incorporates hard and corner cases that are critical yet underrepresented in prior benchmarks, covering 5 major OCR-centric tracks: text recognition, document parsing, document grounding, key information extraction, and document question answering, comprising 7,093 high-difficulty samples. Extensive experiments on 14 advanced LMMs reveal that current models fall short of real-world application requirements. Even state-of-the-art LMMs exhibit substantial performance degradation across diverse tasks and scenarios. These findings reveal a significant gap between performance on current benchmarks and effectiveness in real-world applications. We release the full dataset and evaluation toolkit at https://github.com/eioss/CC-OCR-V2.

How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss discourse structure, while embeddings conflate local coherence with global organization. No existing framework maps these techniques onto the hierarchical processes through which narratives are constructed. Here we introduce a three-level framework - micro-level lexical features, meso-level semantic embeddings, and macro-level LLM narrative evaluation - and show, across 830 Chinese therapeutic texts spanning depression, anxiety, and trauma, that macro-level evaluation substantially outperforms lexical and embedding features for mental health prediction. This challenges the field's emphasis on word-counting: formal structural features (Labov's story grammar, RST coherence, propositional composition) demonstrate that narrative organization per se carries predictive signal, while clinically-grounded narrative dimensions capture how psychological states are expressed through discourse. Semantic embeddings add minimal independent value but yield incremental gains in multi-level classification. By grounding computational levels in discourse processing theory, this framework identifies macro-structural organization as the primary locus of clinical signal and generates testable hypotheses for intervention design and longitudinal research.

Privacy policies are essential for users to understand how service providers handle their personal data. However, these documents are often long and complex, as well as filled with technobabble and legalese, causing users to unknowingly accept terms that may even contradict the law. While summarizing and interpreting these privacy policies is crucial, there is a lack of high-quality English parallel corpus optimized for legal clarity and readability. To address this issue, we introduce APPSI-139, a high-quality English privacy policy corpus meticulously annotated by domain experts, specifically designed for summarization and interpretation tasks. The corpus includes 139 English privacy policies, 15,692 rewritten parallel corpora, and 36,351 fine-grained annotation labels across 11 data practice categories. Concurrently, we propose TCSI-pp-V2, a hybrid privacy policy summarization and interpretation framework that employs an alternating training strategy and coordinates multiple expert modules to effectively balance computational efficiency and accuracy. Experimental results show that the hybrid summarization system built on APPSI-139 corpus and the TCSI-pp-V2 framework outperform large language models, such as GPT-4o and LLaMA-3-70B, in terms of readability and reliability. The source code and dataset are available at https://github.com/EnlightenedAI/APPSI-139.

Document understanding is a critical capability in financial credit review, onboarding, and remote verification, where both decision accuracy and evidence traceability matter. Compared with static document images, document videos present a temporally redundant and sequentially unfolding evidence stream, require evidence integration across frames, and preserve acquisition-process cues relevant to authenticity-sensitive and anti-fraud review. We introduce FCMBench-Video, a benchmark for document-video intelligence that evaluates document perception, temporal grounding, and evidence-grounded reasoning under realistic capture conditions. For privacy-compliant yet realistic data at scale, we organize construction as an atomic-acquisition and composition workflow that records reusable single-document clips, applies controlled degradations, and assembles long-form multi-document videos with prescribed temporal spans. FCMBench-Video is built from 495 atomic videos composed into 1,200 long-form videos paired with 11,322 expert-annotated question--answer instances, covering 28 document types over 20s--60s duration tiers and 5,960 Chinese / 5,362 English instances. Evaluations on nine recent Video-MLLMs show that FCMBench-Video provides meaningful separation across systems and capabilities: counting is the most duration-sensitive task, Cross-Document Validation and Evidence-Grounded Selection probe higher-level evidence integration, and Visual Prompt Injection provides a complementary robustness dimension. The overall score distribution is broad and approximately bell-shaped, indicating a benchmark that is neither saturated nor dominated by trivial cases. Together, these results position FCMBench-Video as a reproducible benchmark for tracking Video-MLLM progress on document-video understanding and probing capability boundaries in authenticity-sensitive credit-domain applications.

While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constrains performance on specialized, non-generative tasks. We attribute this performance bottleneck to the LLMs' knowledge expression mechanism, rather than to deficiencies in knowledge acquisition. To address this, we propose Self-Knowledge Re-expression (SKR), a novel, task-agnostic adaptation method. SKR transforms the LLM's output from generic token generation to highly efficient, task-specific expression. SKR is a fully local method that uses only unannotated data, requiring neither human supervision nor model distillation. Experiments on a large financial document dataset demonstrate substantial improvements: over 40% in Recall@1 for information retrieval tasks, over 76% reduction in object detection latency, and over 33% increase in anomaly detection AUPRC. Our results on the MMDocRAG dataset surpass those of leading retrieval models by at least 12.6%.

Handwritten Arabic manuscripts preserve the Arab world's intellectual and cultural heritage, and writer identification supports provenance, authenticity verification, and historical analysis. Using the Muharaf dataset of historical Arabic manuscripts, we evaluate writer identification from individual line images and, to the best of our knowledge, provide the first baselines reported under both line-level and page-disjoint evaluation protocols. Since the dataset is only partially labeled for writer identification, we manually verified and expanded writer labels in the public portion from 6,858 (28.00%) to 21,249 lines (86.75%) out of 24,495 line images, correcting inconsistencies and removing non-handwritten text. After further filtering, we retained 18,987 lines (77.51%). We propose a Convolutional Neural Network (CNN)-based model with attention mechanisms for closed-set writer identification, including rare two-writer lines modeled as composite writer-pair classes. We benchmark fourteen configurations and conduct ablations across different feature extractors and training regimes. To assess generalization to unseen pages, the page-disjoint protocol assigns all lines from each page to a single split. Under the line-level protocol, a fine-tuned DenseNet201 with attention achieves 99.05% Top-1 accuracy, 99.73% Top-5 accuracy, and 97.44% F1-score. Under the more challenging page-disjoint protocol, the best observed results are 78.61% Top-1 accuracy, 87.79% Top-5 accuracy, and 66.55% F1-score, thus quantifying the impact of page-level cues. By expanding the Muharaf dataset's labeled subset and reporting both protocols, we provide a clearer benchmark and a practical resource for historians and linguists engaged with culturally and historically significant documents. The code and implementation details are available on GitHub.

We introduce MMTR-Bench, a benchmark designed to evaluate the intrinsic ability of Multimodal Large Language Models (MLLMs) to reconstruct masked text directly from visual context. Unlike conventional question-answering tasks, MMTR-Bench eliminates explicit prompts, requiring models to recover masked text from single- or multi-page inputs across real-world domains such as documents and webpages. This design isolates the reconstruction task from instruction-following abilities, enabling a direct assessment of a model's layout understanding, visual grounding, and knowledge integration. MMTR-Bench comprises 2,771 test samples spanning multiple languages and varying target lengths. To account for this diversity, we propose a level-aware evaluation protocol. Experiments on representative MLLMs show that the benchmark poses a significant challenge, especially for sentence- and paragraph-level reconstruction. The homepage is available at https://mmtr-bench-dataset.github.io/MMTR-Bench/.

Research artifacts are distributed primarily as reader-oriented documents like PDFs. This creates a bottleneck for increasingly agent-assisted and agent-native research workflows, in which LLM agents need to infer fine-grained, task-relevant information from lengthy full documents, a process that is expensive, repetitive, and unstable at scale. We introduce Knows, a lightweight companion specification that binds structured claims, evidence, provenance, and verifiable relations to existing research artifacts in a form LLM agents can consume directly. Knows addresses the gap with a thin YAML sidecar (KnowsRecord) that coexists with the original PDF, requiring no changes to the publication itself, and validated by a deterministic schema linter. We evaluate Knows on 140 comprehension questions across 20 papers spanning 14 academic disciplines, comparing PDF-only, sidecar-only, and hybrid conditions across six LLM agents of varying capacity. Weak models (0.8B--2B parameters) improve from 19--25% to 47--67% accuracy (+29 to +42 percentage points) when reading sidecar instead of PDF, while consuming 29--86% fewer input tokens; an LLM-as-judge re-scoring confirms that weak-model sidecar accuracy (75--77%) approaches stronger-model PDF accuracy (78--83%). Beyond this controlled evaluation, a community sidecar hub at https://knows.academy/ has already indexed over ten thousand publications and continues to grow daily, providing independent evidence that the format is adoption-ready at scale.

Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems typically rely on generic retrieval signals that overlook the fine-grained visual semantics essential for complex reasoning. To address this limitation, we propose UniDoc-RL, a unified reinforcement learning framework in which an LVLM agent jointly performs retrieval, reranking, active visual perception, and reasoning. UniDoc-RL formulates visual information acquisition as a sequential decision-making problem with a hierarchical action space. Specifically, it progressively refines visual evidence from coarse-grained document retrieval to fine-grained image selection and active region cropping, allowing the model to suppress irrelevant content and attend to information-dense regions. For effective end-to-end training, we introduce a dense multi-reward scheme that provides task-aware supervision for each action. Based on Group Relative Policy Optimization (GRPO), UniDoc-RL aligns agent behavior with multiple objectives without relying on a separate value network. To support this training paradigm, we curate a comprehensive dataset of high-quality reasoning trajectories with fine-grained action annotations. Experiments on three benchmarks demonstrate that UniDoc-RL consistently surpasses state-of-the-art baselines, yielding up to 17.7% gains over prior RL-based methods.

Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined topics together with manually annotated spans and supporting evaluation at both document and word levels. Evaluation is performed relative to human agreement rather than a single reference annotation. We evaluate a diverse range of large language models alongside BERT-based models fine-tuned on a distilled development dataset. Results reveal substantial variability among LLMs, with performance ranging from near-human topic detection to pronounced failures in span localization. While the strongest models approach human agreement, the distilled token embedding models remain competitive despite their smaller scale. The dataset and evaluation framework are publicly available at: https://github.com/dcgm/czechtopic.

Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)

The narrative composition of web-scale LLM pretraining corpora remains largely unexplored, even though narrative is a fundamental mode of human communication. We present the first fine-grained study of narrative features in Dolma, a 3-trillion-token open pretraining corpus. Drawing on narrative theory, we design a framework spanning three core narrative elements (agency, setting, and events) operationalized as 11 interpretable dimensions. After curating and hand-annotating a diverse set of 400 passages, we create an LLM-labeled dataset of 25K passages, and finally, we finetune and validate NarraBERT, two RoBERTa-based models for fine-grained narrative prediction. We apply NarraBERT to 13M passages, resulting in a new dataset, NarraDolma. We find that narrative structure is measurable at scale across extremely heterogeneous data and narrative qualities are unequally distributed across pretraining sources, topics, and formats in ways that current data curation practices neither measure nor account for. Our framework, dataset, and analyses provide a foundation for understanding how narrative qualities are distributed in LLM pretraining data.