# Thinking with Anchors: Grounded and Efficient Document Reasoning

arXiv: https://arxiv.org/abs/2608.04424 · HTML: https://mlsanity.com/paper/2608.04424/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 78 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Fast-dLLM v2: Efficient Block-Diffusion LLM](https://mlsanity.com/paper/2509.26328/) (2025)
- [SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation](https://mlsanity.com/paper/2510.06303/) (2025)
- [MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm](https://mlsanity.com/paper/2506.05218/) (2025)
- [DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception](https://mlsanity.com/paper/2410.12628/) (2024)
- [DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models](https://mlsanity.com/paper/2406.11633/) (2024)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [CountQA: How Well Do MLLMs Count in the Wild?](https://mlsanity.com/paper/2508.06585/) (2025)
- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [Kwai Keye-VL-2.0 Technical Report](https://mlsanity.com/paper/2606.10651/) (2026)
- [Diachronic Document Dataset for Semantic Layout Analysis](https://mlsanity.com/paper/2411.10068/) (2024)
- [DocAtlas: Multilingual Document Understanding Across 80+ Languages](https://mlsanity.com/paper/2605.12623/) (2026)
- [HoloCount: A Holistic Visual Counting Benchmark for MLLMs](https://mlsanity.com/paper/2607.06420/) (2026)

## Abstract (arXiv)

Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reason jointly about region semantics, spatial relations, and visual structure. We present ADOPD 2026, a reasoning-oriented extension of ADOPD that turns page decomposition into spatially grounded document understanding. ADOPD 2026 enriches page anchors inherited from ADOPD 2024 dataset with human-cleaned captions, semantic tags, and generated chain-of-thought (CoT) traces grounded to document regions. Instead of treating boxes, masks, and tags as independent supervision signals, we cast text blocks, visual entities, semantic labels, bounding boxes, and polygon masks as a shared vocabulary of visual anchors. This representation supports three connected capabilities. First, region-level semantic tagging asks models to identify document element types from both page context and local appearance, revealing long-tail semantic failures that standard layout benchmarks often hide. Second, unified vision-language grounding generates text regions and visual entities together with coordinates or polygonal outlines, transforming detection and segmentation outputs into structured anchors that can be reused by downstream reasoning systems. Third, current state-of-the-art models still struggle with dense counting tasks evaluated on DocCount, a benchmark derived from ADOPD 2026, highlighting the need for the Thinking-with-Anchors pipeline in document semantic understanding. By connecting page decomposition to verifiable visual-anchor reasoning, ADOPD 2026 provides a task framework that moves document understanding beyond localization toward anchor-grounded document intelligence.