SCoPE VLM: Selective Context Processing for Efficient Document Navigation in Vision-Language Models

Challenge:	Existing methods for document understanding are memory-intensive and impractical for local deployments.
Approach:	They propose a document navigation expert that leverages a Chain of Scroll mechanism to selectively and recursively navigate documents, focusing exclusively on relevant segments.
Outcome:	The proposed method reduces memory usage and effectively models human-like reading behaviors.

Similar Papers

Overview

Challenge

Approach

Outcome

ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents (2026.acl-long)

Copied to clipboard

Tianyu Yang, Terry Ruas, Yijun Tian, Jan Philip Wahle, Daniel Kurzawe, Bela Gipp

Visual Data in NLP

Challenge:	Visually rich documents (VRDs) combine text, tables, and figures within complex, semantically structured layouts.
Approach:	They propose a multi-turn reinforcement learning framework that fine-tunes VLMs as interactive agents capable of actively navigating long, visually rich documents.
Outcome:	The proposed framework achieves state-of-the-art on five long-document benchmarks.

ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use (2026.findings-acl)

Copied to clipboard

Mengjie Deng, Guanting Dong, Zhicheng Dou

Multimodality

Challenge:	Recent advances in large language models have demonstrated remarkable problem-solving capabilities . however, enabling multimodal large language model to flexibly and efficiently utilize external tools remains a challenge .
Approach:	They introduce an agentic framework to unify global planning with local multimodal perception . they evaluate ToolScope on four VQA benchmarks across diverse domains .
Outcome:	The proposed framework unifies global planning with local multimodal perception . it adopts a specialized Perceive tool to mitigate visual context degradation in long-horizon VQA task.

Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)

Copied to clipboard

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

Multimodality

Challenge:	Existing OCR-free approaches to document visual question answering are brittle and passive.
Approach:	They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Outcome:	The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline.

SCOPE: Boosting LLM Efficiency with Scoped Position Encoding (2026.acl-long)

Copied to clipboard

Qingguo Qi, Hongyang Chen, Zhao Li

Green & Sustainable NLP

Challenge:	Positional encodings are fundamental to Transformers, but explicit methods like RoPE can degrade under length extrapolation and incur extra arithmetic and memory-access overhead.
Approach:	They propose a framework that reimagines structured sparsity as an intrinsic position encoding mechanism.
Outcome:	The proposed framework reduces the number of attention FLOPs by 8x compared to RoPE on LLaMA-3-8B architectures while reducing training and inference latency.

DocAgent: An Agentic Framework for Multi-Modal Long-Context Document Understanding (2025.emnlp-main)

Copied to clipboard

Li Sun, Liu He, Shuyue Jia, Yangfan He, Chenyu You

Multimodality

Challenge:	Existing approaches to document understanding are limited due to limited context length or fail to fully leverage multi-modal information.
Approach:	They propose a multi-agent framework for long-context document understanding that imitates human reading practice.
Outcome:	The proposed framework surpasses human-level benchmarks on long-context document understanding while maintaining a short context length.

DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding (2026.acl-long)

Copied to clipboard

Dawei Zhu, Rui Meng, Jiefeng Chen, Sujian Li, Tomas Pfister, Jinsung Yoon

Multimodality

Challenge:	Existing approaches to localizing evidence from long visual documents fail on a fundamental challenge: evidence localization.
Approach:	They propose a tool-augmented multi-agent framework that “zooms in” on evidence like a lens.
Outcome:	The proposed framework achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts.

MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding (2024.findings-emnlp)

Copied to clipboard

Qinzhuo Wu, Weikai Xu, Wei Liu, Tao Tan, Liujian Liujianfeng, Ang Li, Jian Luan, Bin Wang, Shuo Shang

Semantic Text Processing

Challenge:	Recent mobile AI agents based on VLMs lack basic mobile capabilities due to their pre-trained nature.
Approach:	They propose a mobile AI agent based on VLMs that includes additional pre-training stages to enhance both intra- and inter-UI understanding.
Outcome:	The proposed model outperforms existing VLMs on the Chinese mobile dataset Mobile3M .

Attention as Selector: Unlocking VLM Attention for Long Document Page Retrieval (2026.acl-long)

Copied to clipboard

Minfeng Zhu, Linxin Bao, Wei Chen, Linchao Zhu

Multimodality

Challenge:	Existing page-level retrieval methods lack query–page interaction before similarity scoring . Existing methods require large-scale datasets to align visual and textual embeddings .
Approach:	They propose a retrieval framework that utilizes attention mechanisms inside VLMs for page selection.
Outcome:	The proposed retrieval framework outperforms embedding-based retrieval methods on four long-document benchmarks.

On the Fine-Grained Planning Abilities of VLM Web Agents (2025.findings-emnlp)

Copied to clipboard

Surgan Jandial, Yinong Oliver Wang, Andrea Bajcsy, Fernando De la Torre

Challenge:	Vision-Language Models (VLMs) have shown promise as web agents, yet their planning has been overlooked.
Approach:	They propose to examine VLMs’ ability to understand temporal relationships within web contexts and assess plans of actions across diverse scenarios.
Outcome:	The proposed models exhibit limited performance in the above skills and are not reliable to function as web agents.

VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation Agents (2026.acl-long)

Copied to clipboard

Xunyi Zhao, Gengze Zhou, Qi Wu

Multimodality

Challenge:	Multimodal Large Language Models have demonstrated remarkable capabilities across vision-language tasks, but their performance as embodied agents needs further exploration.
Approach:	They propose a framework to evaluate multimodal large language models as zero-shot agents . they find that enhancing prevalent agents with Chain-of-Thought reasoning and self-reflection leads to an unexpected performance decrease.
Outcome:	The proposed framework enables comparisons and component-level ablations across diverse MLLM architectures, agent designs, and navigation tasks.