Preprint

RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation

Jia-Yang Yu Jialun Zhong Lei Zou

Aug 2026 · 0 citations · 38 references

Computer Science

TL;DR

This work introduces RAGOCR, a novel framework that compresses retrieved documents into compact visual representations conditioned on the input query, and introduces a query-aware dynamic resolution mechanism that adaptively allocates visual granularity based on each document's estimated relevance and complexity.

Abstract

Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computational cost of processing lengthy retrieved contexts. Existing compression approaches face a fundamental trade-off: hard compression methods operate online in a query-aware fashion but achieve only modest compression rates and typically require fine-tuning the generative model, while soft compression methods attain higher ratios but rely on costly offline encoding that is entirely agnostic to the input query. To bridge this gap, we introduce RAGOCR, a novel framework that compresses retrieved documents into compact visual representations conditioned on the input query. To further balance compression rate and information fidelity, we introduce a query-aware dynamic resolution mechanism that adaptively allocates visual granularity based on each document's estimated relevance and complexity: highly relevant passages are rendered at higher resolution to preserve fine-grained details, while peripheral documents are aggressively compressed at lower resolution. Experiments on five QA benchmarks using the MedOmniKB retrieval corpus demonstrate that RAGOCR surpasses naive RAG by over 15\% in accuracy while requiring only one-eighth the number of input tokens, and consistently outperforms both hard and soft compression baselines across varying retrieval depths.

arXiv Semantic Scholar

View source

Similar papers

Preprint Aug 2026

Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation

Doc-REFRAG, a question-guided framework that compresses visual tokens into coarse chunks and selectively expands question-relevant ones via a lightweight RL-based selector, is proposed, achieving state-of-the-art accuracy with significantly lower inference latency.

Ruofan Hu, Sheng Xu, Minjie Hong et al. · 0 citations

#natural language process... Preprint Sep 2026

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades inference efficiency. Soft context compression encodes each document into a substantially shorter embedding sequence. However, most existing approaches are trained by distilling outputs from uncompressed RAG systems, inherently limiting their performance relative to the original model. To address this limitation, we propose DEX-Comp, a two-stage training recipe: Pure Distillation warm-starts the compression model on the uncompressed RAG's correct responses only, and Hard Exploration then runs reinforcement learning solely on queries the uncompressed RAG fails, forcing the model to explore computation patterns better suited to compressed representations. On five open-domain QA benchmarks at retrieval depths from top-5 to top-30, DEX-Comp compresses retrieved contexts by $16\times$ and accelerates inference by $4\times$--$24\times$, while achieving performance comparable to or exceeding the uncompressed RAG baseline across retrieval depths. Ablations and evaluations across diverse datasets and backbones further confirm the contribution of each stage and the generalization of our approach.

Shuyu Guo, Shuo Zhang, Zhao-Chun Ren · 0 citations

Preprint Aug 2026

SEER: Long-Context Reasoning via Selective Visual-Text Compression

SEER is presented, a framework that learns to select query-relevant images through visual scanning and retrieve textual content only where needed, combining the efficiency of visual compression with the precision of text-based reasoning.

Jiawei Xu, Zhilin Zhai, Jinrui Fang et al. · 0 citations

Preprint Aug 2026

Learning Sample-wise Rank-aware Interpolation Weights for Composed Visual Data Retrieval

This work revisits the efficacy of simple linear interpolation within an embedding space, and introduces SRAIN, the first framework that dynamically predicts query-specific interpolation weights, and achieves the best in composed video retrieval and matches the current state of the art in composed image retrieval.

Boseung Jeong, T. Park, Donghyeon Kwon et al. · 1 citation

Open access 2026

SAC-RAG: Semantic Adaptive Context Compression for Retrieval-Augmented Generation

Experimental results show that SAC-RAG reduces token consumption by 38%–58% at the cost of only a 1–2 percentage point EM drop, with EM actually improving after compression for reasoning-type questions, achieving the optimal quality–efficiency trade-off in terms of token consumption.

Deyu Zhang, Hongqiang Yu, Jinze Huo et al. · IEEE Access · 0 citations

Conference 2026

DARE-RAG: Difficulty-Aware Retrieval Expansion for Retrieval-Augmented Generation

DARE-RAG is proposed, an adaptive retrieval framework that activates LLM-based query expansion only for retrieval-challenging queries, and formulates expansion activation as a lightweight binary classification problem using probe retrieval signals, including score margin, variance, entropy, query length, and lexical specificity.

Li-Xiang Zhu · Poster Volume 0007 The 2026... · 0 citations