Document QA

QA: Question Answering

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 52

Oct 7, 2026cs.IR

From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA

Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not model reasoning but a mismatch between a query and the way knowledge is organized for retrieval. This mismatch is pronounced in Electronic Design Automation (EDA) documentation, where the information needed for an answer is scattered across heterogeneous yet tightly coupled artifacts. We therefore redesign the basic retrieval unit of RAG. Instead of operating on isolated chunks or binary relations, we collect typed artifacts into EDA functional units. Each unit is recorded as a hyperedge with links to its source chunks. We then train an encoder to align queries with functional units and combine unit retrieval with direct chunk retrieval. After mapping the selected units back to their sources, a unified reranker chooses the evidence given to the generator. On the newly constructed EDADocEval-QA dataset, our method improves ROUGE-L by 37.1% over Chunk RAG and 55.6% over the strongest graph baseline. On the public ORD-MMBench benchmark, it improves ROUGE-L by 30.0% over the strongest baseline. These results support function-aware evidence organization in the evaluated EDA documentation settings.

Xiaotian Qiu, Kairui Liu, Shi Chenyi +3

Zhejiang University · Shanghai Innovation Institute

Evidence Retrieval Retrieval-Augmented Generation Document QA Graph-Based Retrieval Electronic Design Automation

Sep 28, 2026cs.CL

When Harness Beats Scale, and When Reading Beats Both

We describe our system for DocSem, the document-grounded quantitative reasoning shared task at DocInsights 2026, and analyze why it succeeded on labeled data and failed on the test set. The pipeline pairs hybrid block retrieval with Program-of-Thoughts (PoT) generation executed in a sandboxed interpreter, self-consistency sampling, and entity enrichment from chunk-level knowledge graphs. On our held-out split, application architecture moved the metrics far more than model scale did: PoT added 0.282 joint accuracy to a compact 7B model but at most 0.005 to a 72B model, and a 27B model with the full harness matched the 72B (0.884 vs.\ 0.873) at roughly 2.7

\times

fewer parameters and a quarter of the CO

_2

. We read this through a distinction between world knowledge, which scales steeply with parameters, and language knowledge, which scales gently, and show that structured-output training makes a compact model harness-ready rather than merely small. On the raster, watermarked test PDFs the same system collapsed to 13.58% joint (rank 149 of 163); a controlled re-rendering of the validation set reproduces the OCR half of the collapse while bounding what the simulation misses. Auditing the physical nature of evaluation inputs precedes architecture, and the leaderboard's bimodality is consistent with reading quality, not reasoning, having separated the field.

Ivan Bondarenko, Nikolay O. Nikitin

Novosibirsk State University · ITMO University

Numerical Reasoning in Language Models Language Model Scaling Document QA

Sep 24, 2026cs.CL

An Empirical Study of VLM Pipelines for Long-Document QA

Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model agentically or as a static pipeline. We study these choices on two long-document QA benchmarks with both frontier API and open-weight VLMs. First, on MMLongBench-Doc our six-tool agent with page, table, figure, and search calls pays off only once the answering VLM is large enough: with Qwen3.5-4B and 9B it trails static page input, with Qwen3.5-27B it draws level, and with Sonnet 4.5 it leads. On LongDocURL it is level with or ahead of static input at every reader. Its lead over the strongest static pipeline is clearest with the frontier reader on MMLongBench-Doc and narrows to within noise on LongDocURL. Second, retrieval modality matters more than the specific retriever: the strongest image retriever leads the strongest text pipeline, and on the text side a single off-the-shelf cross-encoder rerank essentially matches a much heavier multi-stage LLM pipeline. Top-k image retrieval is also the most token-efficient input at every reader we paired it with, at roughly a seventh to a quarter of the tokens of sending every page. Third, cutting across all three choices, three of our strongest pipelines succeed on different questions, and an oracle that picks the best pipeline per question gains roughly thirteen points over the best single pipeline, though evidence-type routing recovers almost none of it.

Kenan E. Ak, Jay Mohta, Gwang Gook Lee +2

VLM Evaluation Tool Use in VLMs Document QA Visual Document Retrieval Long-Context VLMs

Sep 23, 2026cs.CL

Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints

Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents. This paper evaluates five open-weight 7B-8B models for Turkish document question answering under a resource-constrained local deployment setting. The primary benchmark contains 100 systematically validated questions derived from a 109-page industrial R&D report, and the evaluation protocol is replicated using a second 112-page public-sector report and an independently constructed 100-question set. All models are evaluated locally on an NVIDIA RTX 3050 laptop GPU with 6 GB VRAM using controlled prompting, decoding, and 4-bit quantisation. The principal methodological contribution is an evidence-annotated evaluation protocol that separates retrieval failure from downstream model reasoning failure without requiring additional model calls. On the primary benchmark, end-to-end accuracy ranges from 49% to 75%. Seven lexical, dense, and hybrid retrieval configurations are additionally compared using 95% Wilson intervals and exact paired McNemar tests; none significantly outperforms the character TF-IDF baseline on either document. Evidence recall saturates differently across the two reports, showing that retrieval and effective context capacity can be binding constraints for some documents but not others. These results demonstrate that model selection, retrieval behaviour, and hardware limits must be evaluated separately when deploying open-weight LLMs for Turkish domain documents.

Imtiaz Ul Hassan, Öykü Akbulut, Onur Kaya +4

Edge Hill University, United Kingdom · Ermetal Otomotiv ve E¸sya San. Tic. A.¸S., Türkiye

Multilingual Language Model Evaluation LLM Evaluation Open-Weight Language Models Document QA RAG Evaluation

Sep 16, 2026cs.AI

Version- and Scope-Aware Question Answering over Normative Documents: A Deployed System and an End-to-End Evaluation at Production Scale

Correctly answering a question grounded in normative documents often depends on information outside any single passage: whether the retrieved document is the version currently in force; whether it applies to the jurisdiction, subject (such as an institution or applicant), and date at issue; and whether each normative claim can be traced to its supporting source text. Hosted retrieval services have substantially lowered the engineering cost of building an initial system over such corpora, making "upload the documents and ask" a common default. We evaluate this default on approximately 73,000 candidate normative documents supplied to a production deployment. The evaluation uses a stratified sample of 200 questions from our published benchmark, with a gold source document for every question; the released sampling rule reads no system outputs or scores. We compare the hosted service with a governed system that resolves version and scope through explicit rules before generation. The governed system scored 97.7 overall, while the hosted service scored 88.1, a gap of 9.6 points computed from unrounded means. The question set, the answer text evaluated for both systems, the scores, and the scripts used to reproduce the reported benchmark statistics are public. The governed configuration has operated as a commercial product since January 2026 and serves 1,126 registered users; named customer organizations include Zhipu AI and Lecheng Health. By mid-April 2026, it had reached roughly 100,000 calls per workday.

Liuyin Wang, Shuaipeng Jin, Jiwei Shi +1

Beijing Caizhi Technology Co., Ltd., Beijing, China · dknownAI, Beijing, China

Document QA RAG Evaluation

Sep 16, 2026cs.IR

PageRecall: Measuring Page Selection in Literature-Grounded Question Answering

We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the page and the table or figure where the answer lives, and answer in a requested format. Our main finding is that evidence grounding is limited by retrieval, not by reading. The page selector put the annotator's page, which we call the gold page, in front of the model that locates evidence only about half the time (52.6% gold-page recall), while that model, given the page, cited the right one in 45 of the 48 locators it emitted (94%). When the page was missing it rarely said so: of 45 such cases it returned nothing 14 times, a wrong page 24 times, and a correct page 7 times, so the pipeline failed quietly almost twice as often as it failed visibly. Since the failure was that the right page was never shown, the fix is to stop choosing: each retrieved paper fits in the model's context, so we show it whole. Page ranking survives only as a fallback inside papers too long to fit, which no test-split paper was, and gold-page recall reaches 100% on the papers we can parse. Separately, questions that identify their target by position rather than content, such as "the first author of the 24th reference", are served by parsing rather than retrieval: we resolve the bibliography into an addressable list, which also supplies identifiers the evidence metric scores. The final system scores 0.762 paper

F_1

, 0.441 evidence

F_1

and 0.920 multiple-choice accuracy on the held-out test split. Because the pipeline depends on a closed model without seed control, we release a harness that verifies the paper's central claims against committed artifacts.

Aaditya Chauhan

Independent Researcher

Document Information Extraction Scientific QA Document QA Evidence Retrieval

Sep 4, 2026cs.AI

SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding

Scientific papers require models to integrate evidence across text, equations, figures, tables, code, and datasets while preserving its provenance. Beyond answer correctness, scientific reading requires verifiable outputs from operations such as evidence localization, definition extraction, and consistency checking. We introduce SciDocBench, a workflow-centered benchmark targeting these operations through 124 expert-authored and difficulty-screened questions across seven research-assistant capability groups, 19 subtasks, and five scientific domains. Each question is instantiated in four matched settings formed by pairing its bilingual variants with the All Images First and Markdown Interleaved document representations, yielding 496 evaluation instances. The strongest evaluated model, Claude-Opus-5, scores 62.6 out of 100, with remaining gaps in evidence localization, structured information extraction, cross-document synthesis, and robustness to document representation. To convert these diagnostics into scalable training signals, we introduce SciDocIR, a structured representation of scientific document objects, layout and cross-reference relations, and provenance. Using SciDocIR, we construct SciDocDataset, which contains 4K supervised fine-tuning instances and 10K reinforcement-learning instances, built on 14 verifiable training subtasks. Post-training Qwen3.6-27B on task-aligned data improves its SciDocBench score from 40.03 to 45.33 with supervised fine-tuning and to 45.74 with subsequent reinforcement learning. Both adapted models preserve DocVQA and InfoVQA performance and improve ChartQA accuracy over the original model by 0.80 and 3.40 points, respectively. Together, SciDocBench, SciDocIR, and SciDocDataset connect capability diagnosis with verifiable training-data construction for scientific-document assistants.

Shenxi Wu, Yuhong Liu, Haosong Zhang +8

The Chinese University of Hong Kong · Shanghai Artificial Intelligence Laboratory · New York University +5

Document Understanding LLM Evaluation Document Information Extraction Scientific QA Document QA

Aug 9, 2026cs.AI

From Manuals to Maintenance: Fine-Tuning MedGemma for Multi-Modal Imaging System Support in Low-Resource Settings

Imaging device downtime is a major barrier to healthcare delivery in low- and middle-income countries (LMICs), often driven by limited access to specialized biomedical engineering support. We present a multi-modality medical equipment maintenance question-answering (QA) framework and demonstrate the fine-tuning of a medical foundation model for specialized technical troubleshooting tasks. Guided by a multi-country survey across nine LMICs, we curated technical manuals from MRI and ultrasound systems to generate the INGENZI_DatasetV1, containing 10,294 high-quality, filtered QA-context pairs. Using QLoRA-based parameter-efficient fine-tuning, we adapted the MedGemma-4b-it model to interpret system error logs and generate step-by-step equipment repair instructions. Compared to the baseline model, the fine-tuned system achieved substantial improvements across metrics, including F1 score (0.22 to 0.38), ROUGE-2 (0.18 to 0.41), and BERTScore F1 (0.86 to 0.91). These metric gains demonstrate that the model generates significantly more precise and procedurally accurate technical responses to new troubleshooting queries. This work establishes a reliable foundation for AI-assisted diagnostic and maintenance tools in resource-constrained settings.

Bernes Lorier Atabonfack, Zion Kongbi Nfo, Ahmed Tahiru Issah +9

Carnegie Mellon University Africa, Kigali, Rwanda · IngenziAI, Kigali, Rwanda · Medical Artificial Intelligence Laboratory, Lagos, Nigeria +5

LLM Fine-Tuning Document QA Medical LLMs Fault Diagnosis

Aug 9, 2026cs.AI

Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding

Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time, so a question has different correct answers at different dates. In contrast to encyclopedic knowledge, where an old fact is simply overwritten, an amendment is itself an official text that states what it replaces and when it takes effect, and the earlier version stays correct for its validity period. The central challenge is therefore version resolution, that is, identifying the version in force on the queried date. Existing temporal QA datasets treat time only as an annotation, so version resolution stays untested. We present TIDE, an expert-verified benchmark of 3,050 QA pairs over 644 official customs instruments issued between 1969 and 2025 by the Government of Bangladesh, covering eight task types over deeply code-mixed documents that are heterogeneous in layout and dated in two calendars. In addition, we evaluate nine recent LLMs under a single protocol across parametric, gold-context, and retrieval access, scored by a three-judge LLM council with a hard date gate separating correct meaning from correct time. The best macro-averaged accuracy is only 68.5%. Resolving a version from an implicit date reaches 59.7%, and detecting that the supplied version does not govern the query reaches only 26.7%. Models are more likely to find correct versions than to reject incorrect ones, and they tend to follow a confident parametric answer over the supplied authoritative text. All code and data are available at https://github.com/icsetepa44/TIDE

Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Fahmid Hasan Chowdhury +4

1BRAC University · 2United International University · 3North South University +1

LLM Evaluation Document QA Legal QA Temporal QA

Aug 7, 2026cs.AI

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-

k

page set at the outset and struggle to recover from early retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation mechanism of cross-round states, making it difficult to track the dynamic changes in page relevance. To address these limitations, we propose DocMemo, a memory-guided framework that formulates long-document reasoning as dynamic evidence exploration. DocMemo maintains a tri-level retrieval state consisting of Document Schema Memory, Page Belief Memory, and Question Episodic Memory, which respectively capture structural priors, dynamic relevance estimation, and query-specific reasoning trajectories. During reasoning, DocMemo continuously refines cross-round page selection through Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access, while supplementing page-level evidence with fine-grained visual regions. Experiments on 3 benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured memory and dynamic page belief updating. Code is available at https://github.com/Harrygof/DocMemo.

Hanshu Yao, Janfeng Zhong, Niu Lian +1

1Harbin Institute of Technology, Shenzhen · 2Tsinghua Shenzhen International Graduate School, Tsinghua University

Multimodal Memory Document QA Visual Document Retrieval Evidence Retrieval Multimodal Learning

Aug 6, 2026cs.AI

Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations

Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundary routinely separates a number from whether it is in lakh or crore, an error of two orders of magnitude. A table-aware chunker built as a steelman fixes the unit problem but leaves 27-30% of numeric chunks with no fiscal-year header at every chunk size we tried. We propose READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations -- normalized lexical search, structural navigation, and bounded span reads -- exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score. On 51 verified questions READ answers 58.8% against dense retrieval's 15.7% (p_Holm = 2 x 10^-5) -- or 35.3% tuned, which READ still leads by 23.5 points (p_Holm = 0.017). An agent given the same loop but a top-k tool reaches only 27.5%, locating the gain in the interface rather than in iteration. We also report what the evidence does not support: BM25 is statistically indistinguishable from READ, so our result separates embedding-based from embedding-free retrieval, not agentic from lexical search.

Sagar Tamang, Ayush Vyas, Tabarakul Hazarika

1Indian Institute of Technology Patna, Bihta, India · 2TwoSpoon, India.

Long-Context Retrieval Retrieval-Augmented Generation Agentic Retrieval Document QA Information Retrieval

Aug 4, 2026cs.AI

MMLongBench-Doc-V2: A Corrected-Annotation, Semantics-Aware Revision of MMLongBench-Doc

MMLongBench-Doc is a long-document QA benchmark of 1,082 questions over 135 PDFs. Two properties of it push measured scores away from the quantity they are meant to capture: the reference metric compares extracted answers, so 1,358,000 loses to 1358000; and a non-trivial share of ground-truth annotations are wrong, ambiguous, or incomplete --- concentrated, because of how they were found, in exactly the questions capable systems answer correctly. MMLongBench-Doc-V2 corrects 106 annotations, each published with the page and arithmetic that settle it, and replaces the string metric with a pinned LLM judge asked whether a response means the reference. Ten questions whose document ships under the wrong filename are removed rather than counted wrong, along with one duplicated question, leaving 1,071 questions over 134 documents. The most reusable contribution is a decision procedure for when an empty set key may be widened and when widening would destroy a deliberate negative sample; applied to all 208 rows, it widened 14. V2 scores are not comparable with published V1 numbers. The corrected corpus, the per-entry correction record and the evaluation harness are available at https://github.com/VectifyAI/MMLongBench-Doc-V2.

Mingtian Zhang

PageIndex

LLM Evaluation Long-Context Language Model Evaluation Document QA

Aug 3, 2026cs.CL

DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering

Answering complex questions over large document collections requires assembling complementary evidence across sections and documents. GraphRAG offers structured retrieval but typically uses fixed traversal, while agentic RAG operates over weakly structured interfaces. Our key insight is that agents should navigate document structure within and across documents rather than repeatedly search from scratch. We introduce DocNavRAG, which organizes document hierarchies and cross-region relations into a navigable graph, exposes graph operations for locating, navigating, expanding, and fetching, and maintains an evolving evidence state to guide retrieval until sufficient evidence is collected. Across four long- and multi-document QA benchmarks, DocNavRAG improves answer quality and context sufficiency over the strongest baseline by 7.8% and 17.7% on average.

Dongyang Xie, Yao Tian, Hao Zhang +5

School of Computer Science, Wuhan University · The Hong Kong University of Science and Technology · The Chinese University of Hong Kong +1

Graph Retrieval-Augmented Generation Agentic RAG Document QA Information Retrieval Evidence Retrieval

Jul 31, 2026cs.CV

HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering

Multi-page document visual question answering requires locating sparse evidence at both the page and region levels. Existing approaches typically emphasize one level over the other: page-centric methods focus on page acquisition, with region operations serving mainly as navigation aids, whereas region-centric methods assume that the relevant pages have already been supplied. Consequently, page and region selection remain disconnected rather than forming successive evidence decisions. We propose HierDoc, a hierarchical evidence-routing framework that formulates long-document evidence acquisition as two-stage set prediction from pages to regions. A page policy selects evidence pages from the full document; these pages are then parsed for semantic elements, after which a region policy selects the elements passed to a downstream answer model. Both answer-agnostic policies are optimized with stage-wise GRPO using granularity-specific structured-set rewards. The answer model receives selected full pages together with selected region crops and OCR or table text, preserving global context while emphasizing fine-grained evidence. Across the evaluated benchmarks, HierDoc achieves state-of-the-art or competitive performance among open-weight systems, improving LongDocURL by 16.87% relative to the strongest reported open-weight baseline. Controlled ablations further show that selected regional evidence improves the page-only system in accuracy and F1 by 5.51% and 4.82%, respectively. These results demonstrate the benefit of organizing coarse page routing and fine-grained region routing as successive, separately optimized stages of a unified evidence-acquisition process.

Rongjian Gu, Wengang Zhou, Junyu Xiong +4

University of Science and Technology of China · 2iFLYTEK Research · 3Anhui Transport Consulting & Design Institute Co. Ltd., Hefei, China

Visual Question Answering Document QA Evidence Retrieval

Jul 26, 2026cs.IR

HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document

Question answering (QA) over complex documents requires models to retrieve and integrate evidence distributed across distant document regions and modalities. Multimodal GraphRAG provides a promising direction by organizing document evidence with graph structures. However, existing methods often suffer from unreliable cross-modal evidence indexing and expensive graph traversal. To address these issues, we propose HVM-GraphRAG, a holistic-view multimodal GraphRAG framework on complex document. HVM-GraphRAG uses a holistic view to guide graph construction, thereby reducing noisy and conflicting graph updates and building reliable indices between concept-level graph nodes and supporting multimodal chunks. During retrieval, HVM-GraphRAG searches over a compact concept-level graph and directly accesses supporting evidence through the constructed index, avoiding costly traversal over dense entity-level graphs. After obtaining the retrieved evidence, HVM-GraphRAG further reorganizes chunks into modality-specific groups, enabling the answering model to better integrate heterogeneous evidence. Experiments on three datasets show that HVM-GraphRAG achieves the best answer performance in most evaluated settings while substantially improving online retrieval efficiency over representative graph-based baselines.

Xin He, Yili Wang, Wenqi Fan +4

Jilin University Changchun, China · The Hong Kong Polytechnic University Hong Kong SAR, China

Multimodal RAG Retrieval-Augmented Generation Graph Retrieval-Augmented Generation Multimodal QA Document QA

Jul 21, 2026cs.CV

TAP-RAG: Task-Aware Policy Control for Long-Document Multimodal Question Answering

Long-document multimodal question answering requires more than retrieving relevant chunks from a large document. Different queries require different evidence behavior. Existing multimodal RAG systems improve evidence access through text chunks, page images, graph links, or heterogeneous document elements, but they often apply a largely query-agnostic evidence-use strategy. We present TAP-RAG, a task-aware policy-controlled RAG framework for long-document multimodal QA. TAP-RAG contains a main controller, the Task-Aware Policy Controller (TAPC), and two policy-guided evidence executors: Task-Aware Query-Guided Flow Diffusion (TA-QFD) and Task-Aware Visual Enhancement (TAVE). For each query, TAPC predicts the task prior, estimates visual/local/global evidence signals, and produces an executable policy. TA-QFD then expands textual and structural evidence over the multimodal document graph, while TAVE selectively inspects page images when visual or layout evidence is needed. A guarded synthesis stage fuses text, visual, and structural evidence and abstains when support is insufficient. On DocBench and MMLongBench-Doc, TAP-RAG achieves the best overall accuracy among the compared systems, improving over a matched multimodal-RAG baseline by +9.1 points (61.1 to 70.2) and +4.5 points (42.2 to 46.7), respectively.

Zhong Ji, Keqi Jin, Yan Zhang +1

School of Electrical and Information Engineering, Tianjin University · The International Joint Institute of Tianjin University, Fuzhou, Tianjin University · Department of Automation, Tsinghua University

Multimodal RAG Retrieval-Augmented Generation Long-Context QA Adaptive RAG Multimodal QA Document QA

Jul 21, 2026cs.CL

DocAtlas: Long-Document Understanding as Mutable-State Interaction

Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-augmented systems usually select evidence from a static index before generation, while recent agentic systems add multi-turn tool use but often rely on frozen proprietary backbones whose behavior is set by prompts. We present DocAtlas, a system that treats long-document understanding as a mutable-state information-seeking process. We instantiate DocAtlas as a mutable document harness: an external environment that determines what document information is searched, read, stored, reviewed, and shown to the model at each step. Given a document and question, the harness exposes search, reading, note-taking, and review tools, maintains a hierarchical tree and note store, and updates both as the agent records evidence. DocAtlas combines self-improving retrieval, selective evidence access, and active working memory under a fixed context budget. The same harness supports inference-time use with large VLMs and end-to-end reinforcement learning for compact VLM agents. With GPT-5.4, DocAtlas reaches 71.4% on MMLongBench-Doc, exceeding the human-expert reference of 65.8%. A Qwen3.5-4B VLM trained with end-to-end RL in the DocAtlas environment reaches 63.7%, compared with a 54.4% direct-input baseline, showing that mutable document-harness design can improve compact document agents by a large margin.

Hongchen Wei, Yuanzhe Wang, Bei Liu +8

Wuhan University · Microsoft

Document Understanding Long-Context QA Long-Context Modeling Agentic RAG Document QA

Jul 21, 2026cs.CL

XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding

Real-world document tasks often ask professionals to answer questions from annual reports, regulations, clinical guidelines, and technical manuals that span hundreds or thousands of pages. Some questions also require comparing related reports. Reliable long-document understanding is therefore a prerequisite for using LLMs in compliance, clinical, financial, and engineering workflows, where decisions must be traceable to specific evidence pages and the cost of an unsupported answer is high -- yet most existing benchmarks still measure short-context or single-page QA. We introduce XL-DocBench, a fully human-verified benchmark for extra-long document understanding, with 1,519 retained questions from six professional domains and contexts up to 2,303 pages. XL-DocBench goes beyond page-level lookup. 1,103 examples (72.6%) use multiple evidence pages. The final set also includes 556 questions (36.6%) that use tables, charts, or figures, and 165 questions (10.9%) that require evidence from multiple documents. Each question has one of twelve reasoning labels, expert-annotated evidence pages, a typed verification rule, and an answer format, including 218 None-answer cases. We build the benchmark with a tree-guided synthesis pipeline followed by artifact filters and full verification by 194 human experts. By coupling extra-long professional contexts with page-level evidence and typed rules, XL-DocBench fills a gap left by prior single-page, short multi-page, or text-only long-context benchmarks, and lets future work attribute system failures to retrieval, evidence use, or rule following rather than to a single leaderboard score. The results show that current systems still struggle with long contexts, multi-page evidence, and structured reasoning over professional documents.

Hongchen Wei, Yuanzhe Wang, Bei Liu +9

1Wuhan University · 2Microsoft

Long-Context Retrieval LLM Evaluation Long-Context QA Document QA Knowledge-Intensive QA

Jul 18, 2026cs.LG

Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context Restoration

Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-text preservation, retrieval budget, retrieval modality, rubric audit, and judge choice all affect the outcome. For example, on PAIM Graphiti wins convincingly but uses 2.6M characters of retrieved context per query, and after controlling for retrieval budget the lead disappears. On PTr, for the systems where BM25 retrieval can be added cleanly, the sparse-dense hybrid is the single most significant intervention: hybrid variants of Simple RAG, Mem0, and Theoria tie for the lead within 0.03 points. Multi-judge and human side-by-side calibration show that LLM-as-a-judge rankings are consistent across frontier judges and agree with human evaluation, with an effective resolution of roughly one point on a ten-point scale. We argue that scientific memory should be evaluated as budgeted, modality-aware context restoration rather than as an unconstrained architecture leaderboard, and we release the datasets, harness, raw outputs, judgments, and scripts to reproduce our results and serve as tools for such evaluation. Our code is available at http://gitlab.com/quantellence/research/scientific-recall-bench , and the datasets are available at http://huggingface.co/datasets/quantellence/srb-data .

Maksim Sheverev, David Finkelstein, Sergey Nikolenko

Quantellence Research · St. Petersburg Department of the Steklov Institute of Mathematics, St. Petersburg, Russia · St. Petersburg State University, St. Petersburg, Russia

LLM Agent Memory AI Agent Benchmarks Memory Agent Benchmarks Document QA RAG Evaluation

Jul 16, 2026cs.AI

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization plateaus, and reasoning-centric Reinforcement Learning (RL), which depends on verbose intermediate traces that inflate inference token cost without clear benefit. We introduce Perception-RFT, a training framework that applies Group Relative Policy Optimization (GRPO) to multimodal document QA, bypassing intermediate reasoning tokens to directly align visual features with structured grounding outputs. To rigorously evaluate the necessity of reasoning, we construct a reasoning variant under identical reward settings. We find that reasoning-enabled models suppress their reasoning traces during training, converging to direct perception-based policies at the 4B parameter scale, reducing per-query inference token length by more than 60%, while reasoning-enabled RL underperforms perception-only training. Through a fine-grained analysis of Qwen3-VL-4B optimization dynamics, we confirm that SFT saturation and cold-start RL instability established in text-domain post-training extend to multimodal, and identify a previously uncharacterized Grounding Divergence: a selective trade-off between semantic robustness and geometric precision on two out of distribution (OOD) benchmarks (4,828 samples) under joint RL optimization. We further show that an early SFT

\rightarrow

RL transition achieves comparable precision with 65% less training data.

Harikrishnan P M, Goutham Vignesh, Ganesh Parab +4

Phi Labs, Quantiphi, India · Phi Labs, Quantiphi, Canada.

Multimodal Grounding Efficient Multimodal Inference Document QA Multimodal Foundation Models RL for VLMs

Jul 13, 2026cs.CV

GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents

A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, construction plans. Benchmarks for document AI have generally measured the required capabilities in isolation: OCR, layout analysis, chart reasoning, table QA, document VQA. A high score on any one of them does not necessarily reveal whether a model can answer a realistic question that someone in the field would actually ask about a specific PDF. GDP_pdf is a benchmark built to measure this directly. It consists of question-document pairs authored by working professionals in ten fields, and a candidate question was kept only when at least two frontier multimodal models failed it in a way that mattered: a wrong answer, missed decisive evidence, or a fabricated claim, rather than a superficial difference such as style. Each item comes with a rubric of atomic criteria, so we can report a graded rubric score as well as a strict task-level pass rate, and each item is tagged against a taxonomy of eleven capabilities in three tiers, spanning text extraction and grounding, table and chart comprehension, cross-referencing, spatial reasoning, and abstention on unsupported queries. We report results for seventeen frontier models on the 100-item benchmark: the best model passes only 30.7% of the items and the worst passes 2%. Most errors trace back to a small set of recurring loss patterns: misaligned tables, misread charts, skipped footnotes and exclusions, miscounted floor-plan symbols, scan noise, and amendments that supersede earlier text.

Suhaas Garre, Emily Ritchie, Sushant Mehta +1

Surge AI

Multimodal Grounding Multimodal Reasoning Document QA Multimodal Model Evaluation

Jul 9, 2026cs.DB

DocMaster: A Hierarchical Structure-Aware System for Document Analysis

Leveraging large language models (LLMs) to analyze complex documents -- such as academic papers, technical manuals, and financial reports -- has emerged as a mainstream and critical task in both research and industry. In practice, users must first filter relevant documents from large collections and then conduct in-depth analysis (e.g. question answering) over the selected subset, yet existing systems flatten documents into plain-text chunks, discarding the rich hierarchical structures (sections, tables, figures, equations) and degrading downstream performance. We present DocMaster, a hierarchical structure-aware document analysis system. DocMaster parses documents into hierarchical document trees preserving original layouts and constructs a structure-aware semantic index that enables accurate document filtering and in-depth analysis. We demonstrate DocMaster through an interactive web interface that enables users to upload document collections, construct tree-based and multi-view semantic indices, filter relevant documents via natural-language conditions, and perform follow-up question answering over the filtered results. The source code, data, and demo are available at https://doc-master.github.io/.

Ziqi Chen, Yingli Zhou, Fangyuan Zhang +3

The Chinese University of Hong Kong, Shenzhen · The Chinese University of Hong Kong · OceanBase, AntGroup

Document Understanding Document QA Information Retrieval

Jul 2, 2026cs.IR

Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside their parameters. We evaluate if cluster-based semantic chunking improves retrieval and answer quality compared to fixed-size and recursive chunking evaluating on long, structured academic theses using the Retrieval Augmented Generation Assessment (RAGAs) framework. RAGAs based faithfulness shows limited reliability in this setup. Performance on fixed versus document specific questions varied substantially, likely related to the formatting of documents and preprocessing. Under the tested configuration, cluster-based chunking did not outperform simpler strategies.

Valentin J. J. Kreileder, Johannes Reisinger, Andreas Fischer

Computer Science · Deggendorf Institute of Technology · Deggendorf, Germany

Document Chunking Retrieval-Augmented Generation Document QA RAG Evaluation

Jul 1, 2026cs.CL

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal attributions have been explored in depth, the multimodal setting remains relatively under-researched. As a result, we introduce MultAttnAttrib, a training-free attribution-generation method that leverages a model's prefill pass, selected attention heads, and calibrated thresholds to locate source evidence within a document. To establish baseline results for the method, we introduce MultAttrEval, a complementary benchmark dataset annotated with fine-grained, ground-truth attributions for answer components grounded in multimodal source documents. To our knowledge, this is the first evaluation dataset designed specifically for multimodal attribution in long-form documents. Experimental results show that MultAttnAttrib consistently outperforms a variety of attribution-generation methods, including several strong prompting-based approaches and matches the latest frontier models such as GPT 5.4. Our method not only substantially improves attribution accuracy for both unimodal and multimodal attribution types, but also produces attributions at up to one-seventh of the direct inference latency compared to prompting on the same base model.

Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7

University of Massachusetts, Amherst · 2Adobe Research, San Jose

Multimodal QA Document QA Multimodal Model Interpretability

Jul 1, 2026cs.CL

Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) increasingly requires models to answer questions from multiple retrieved documents, where only some sources are relevant and the retrieved bundle may contain stale, noisy, or conflicting evidence. Existing contrastive decoding methods primarily focus on resolving conflicts between the model's internal memory and the retrieved context. In contrast, we study the complementary problem of intra-context conflict in multi-document RAG. To evaluate this setting, we introduce DRQA, a factual-conflict question answering benchmark derived from enterprise deep-research scenarios, where answers are grounded in synthetic enterprise-specific facts that are designed not to be recoverable from the model's internal memory. We further propose Dual-Confidence Contrastive Decoding (DCCD), a training-free decoding method that combines document-level confidence, which estimates whether a document appears sufficient for answering the question, with token-level confidence, which estimates whether that document supports a confident next-token prediction. DCCD selects positive and negative document-conditioned streams using these dual-confidence signals and scales a document-level contrast by their confidence margin. Across DRQA and standard multi-document QA benchmarks, DCCD achieves the best average performance among full-context and contrastive decoding baselines, with the largest gains on DRQA. These results highlight the importance of source-aware, confidence-gated decoding when retrieved evidence is internally conflicting.

Raymond Li, Md Tawkat Islam Khondaker, Amirhossein Abaskohi +3

ServiceNow Research · University of British Columbia

Retrieval-Augmented Generation Knowledge Conflicts in Language Models Document QA RAG Evaluation Contrastive Decoding

Jun 28, 2026cs.AI

LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents

Reviewing nuclear regulatory documents requires multi-hop reasoning across tens of thousands of pages, where judgments depend on evidence assembled across multiple chapters. We frame this task as planning: an LLM-based agent observes the evidence collected so far, picks the next document fragment to inspect, and stops when the evidence is sufficient. The agent operates over a vectorless document tree using browse, read, and search tools, and maintains a dynamic knowledge graph (KG) as state. On a 200-question benchmark over NuScale Final Safety Analysis Report (FSAR) documents, the system reaches 81.5% accuracy with a RAGAS Faithfulness of 0.93. The dominant performance factor is planning: against PageIndex, which uses the same document tree without state-conditioned action selection, the gap is +38.0pp (43.5% to 81.5%, p<0.001). The system also outperforms LightRAG (73.0%, p<0.05), HippoRAG (70.5%, p<0.01), and GraphRAG (49.5%, p<0.001), and matches RAPTOR (75.5%, p=0.11) without offline indexing. Edge inference adds 2.8x cost without raising accuracy; we retain it as a traceability module. Of 7,391 inferred edges, 3 Violates edges (0.04%) flag scope boundaries (Q058) and partial conformance (Q176) as typed annotations that a human reviewer can audit.

Mingyu Jeon, Bokyeong Kim, Suwan Cho +2

1MODULABS, Seoul, Republic of Korea · 2Korea Atomic Energy Research Institute, Daejeon, Republic of Korea · University of Science & Technology, Daejeon, Republic of Korea

Retrieval-Augmented Generation Legal Document Analysis Document QA LLM Agent Planning LLM Reasoning

Jun 23, 2026cs.CL

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.

Honglin Guo, Qi Zhang, Yu Zhang +7

Fudan University · Zhejiang University · Shanghai Qiji Zhifeng Co., Ltd.

LLM Grounding Document QA Agentic Reasoning Agent Benchmarks

Jun 18, 2026cs.IR

The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications

Document-grounded assistants built on large language models are increasingly used in high-stakes, knowledge-intensive work. Their usefulness, however, may depend on how evidence is allocated before generation. We investigate such a claim by comparing two grounding architectures: (a) retrieval-augmented generation (RAG) that retrieves a few relevant passages, and (b) long-context prompting, which loads the whole document collection in context. We view these as two regimes of "epistemic access" on an accuracy--cost frontier. We use "epistemic accuracy" to capture model correctness that depends on having the right evidence. We posit that broader access (via long context) can increase it, but with a "token tax" (i.e., a substantial increase in cost due to larger input token consumption). We probe this framing with a case study in manufacturing safety training. Using an expert-validated benchmark, we evaluate 972 answers across three machines, two small language models, and three retrieval/in-context prompting approaches. Long-context prompting achieved the highest correctness (73.1% vs. 65.4% for semantic RAG), but at 26 times the per-query token cost. We interpret this gap as the token tax of broader evidentiary access. We carefully discuss the implications of our findings for resource-constrained organizations.

Austin Hamilton, Ryan Singh, Michael Wise +6

Miami University · University at Buffalo

LLM Grounding LLM Inference LLM Prompting Document QA RAG Evaluation

Jun 15, 2026cs.CV

VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA

Real-world documents combine text with tables, charts, photographs, and diagrams arranged in diverse layouts, yet existing research on multimodal large language models (MLLMs) for document QA predominantly produces text-only responses, underutilizing these visual elements. We introduce VinQA, a dataset for long-form answer generation where cited visual elements are explicitly interleaved with their supporting text and grounded in relevant document pages. To support this task, we study two encoding methods for feeding raw document page images into an MLLM, along with their visual-element citation mechanisms: (1) Page Encoding, which directly encodes full-page images with bounding boxes of visual elements and treats these boxed regions as citable units; and (2) Modality Encoding, which parses each page to extract text and crop visual elements, encodes them separately, and uses these cropped elements as citable units. In our experiments, we propose M-GroSE, a multimodal evaluation framework extending GroUSE to assess answers along four dimensions: completeness, answer relevancy, faithfulness, and unanswerability. We additionally report Visual Source F1 to directly measure visual citation accuracy. Although proprietary frontier models still achieve the best overall scores on the VinQA test split, fine-tuning open Qwen2.5-VL models on the training split substantially improves their performance and narrows this gap. Modality Encoding is initially more robust for complex documents with long text, many visual elements, and diverse citation requirements. After training on VinQA, however, Page Encoding reaches a comparable level, competing effectively even without the explicit parsing used in Modality Encoding. Finally, Visual G-Eval, an MLLM-based judge, confirms that fine-tuned models insert visual elements at semantically appropriate positions with faithful supporting text.

Young Rok Jang, Hyesoo Kong, Kyunghwan An +3

LG AI Research

VLM Evaluation Multimodal Large Language Models Multimodal QA Document QA Multimodal Foundation Models Multimodal Understanding

Jun 14, 2026cs.IR

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval. The benefits reported for these methods come almost exclusively from homogeneous corpora, predominantly Wikipedia prose. Whether they hold on the mixed-format collections common in practice, where code, markdown, tables, scientific PDFs, and prose are interleaved within one corpus, has not been measured. To study this directly, we build \textbf{HetDocQA}, a heterogeneous benchmark with \emph{chunker-agnostic} span-overlap relevance labels and collection-disjoint splits, and pair it with MuSiQue and QASPER as homogeneous controls. We evaluate eight methods on a shared backbone, with bootstrap confidence intervals and multiple-comparison correction. A strong cross-encoder reranker accounts for most of the pipeline's quality; beyond it, only two methods yield reliable gains: query expansion and SSCC. SSCC, a per-source calibrated corrector introduced here, sets a separate acceptance threshold for each score source and helps only on heterogeneous data. The remaining reranking and pool-expansion methods in common use, among them hierarchical summarization, graph expansion, routing, and rank fusion, give no reliable gain once that reranker is present.

Sadanand Singh, Allam Reddy, Manan Chopra

Cascade Research

Cross-Encoder Reranking Learning to Rank Document QA Information Retrieval RAG Evaluation Query Expansion