# DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

arXiv: https://arxiv.org/abs/2605.08888 · HTML: https://mlsanity.com/paper/2605.08888/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 57 references that are in the map.
- First posted on arXiv 9 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 15 of 15)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [ColPali: Efficient Document Retrieval with Vision Language Models](https://mlsanity.com/paper/2407.01449/) (2024)
- [Ministral 3](https://mlsanity.com/paper/2601.08584/) (2026)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing](https://mlsanity.com/paper/2601.21957/) (2026)
- [Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale](https://mlsanity.com/paper/2603.25040/) (2026)
- [Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid](https://mlsanity.com/paper/2408.02034/) (2024)
- [DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding](https://mlsanity.com/paper/2604.12812/) (2026)
- [SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning](https://mlsanity.com/paper/2511.15090/) (2025)
- [SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature](https://mlsanity.com/paper/2601.10108/) (2026)
- [BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence](https://mlsanity.com/paper/2603.07931/) (2026)

## Built on by (most cited first, 3 of 3)

- [WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning](https://mlsanity.com/paper/2607.09328/) (2026)
- [AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents](https://mlsanity.com/paper/2609.05802/) (2026)
- [SpatialASM: Internalizing Active Mentalization for Spatial Reasoning](https://mlsanity.com/paper/2610.13832/) (2026)

## Abstract (arXiv)

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.