Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiankun, Zeng, Shenglai, Guo, Kai, Dai, Xinnan, Liu, Hui, Tang, Jiliang, Chang, Yi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915797057667072
author Zhang, Jiankun
Zeng, Shenglai
Guo, Kai
Dai, Xinnan
Liu, Hui
Tang, Jiliang
Chang, Yi
author_facet Zhang, Jiankun
Zeng, Shenglai
Guo, Kai
Dai, Xinnan
Liu, Hui
Tang, Jiliang
Chang, Yi
contents Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a key paradigm for grounding MLLMs with external knowledge. While query pre-processing (e.g., rewriting) is standard in text-based RAG, existing MRAG pipelines predominantly treat visual inputs as static and immutable, implicitly assuming they are noise-free. However, real-world visual queries are often ``imperfect'' -- suffering from geometric distortions, quality degradation, or semantic ambiguity -- leading to catastrophic retrieval failures. To address this gap, we propose V-QPP-Bench, the first comprehensive benchmark dedicated to Visual Query Pre-processing (V-QPP). We formulate V-QPP as an agentic decision-making task where MLLMs must autonomously diagnose imperfections and deploy perceptual tools to refine queries. Our extensive evaluation across 46,700 imperfect queries and diverse MRAG paradigms reveals three critical insights: (1) Vulnerability -- visual imperfections severely degrade both retrieval recall and end-to-end MRAG performance; (2) Restoration Potential \& Bottleneck -- while oracle preprocessing recovers near-perfect performance, off-the-shelf MLLMs struggle with tool selection and parameter prediction without specialized training; and (3) Training Enhancement -- supervised fine-tuning enables compact models to achieve comparable or superior performance to larger proprietary models, demonstrating the benchmark's value for developing robust MRAG systems The code is available at https://github.com/phycholosogy/VQQP_Bench
format Preprint
id arxiv_https___arxiv_org_abs_2602_13179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation
Zhang, Jiankun
Zeng, Shenglai
Guo, Kai
Dai, Xinnan
Liu, Hui
Tang, Jiliang
Chang, Yi
Information Retrieval
Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a key paradigm for grounding MLLMs with external knowledge. While query pre-processing (e.g., rewriting) is standard in text-based RAG, existing MRAG pipelines predominantly treat visual inputs as static and immutable, implicitly assuming they are noise-free. However, real-world visual queries are often ``imperfect'' -- suffering from geometric distortions, quality degradation, or semantic ambiguity -- leading to catastrophic retrieval failures. To address this gap, we propose V-QPP-Bench, the first comprehensive benchmark dedicated to Visual Query Pre-processing (V-QPP). We formulate V-QPP as an agentic decision-making task where MLLMs must autonomously diagnose imperfections and deploy perceptual tools to refine queries. Our extensive evaluation across 46,700 imperfect queries and diverse MRAG paradigms reveals three critical insights: (1) Vulnerability -- visual imperfections severely degrade both retrieval recall and end-to-end MRAG performance; (2) Restoration Potential \& Bottleneck -- while oracle preprocessing recovers near-perfect performance, off-the-shelf MLLMs struggle with tool selection and parameter prediction without specialized training; and (3) Training Enhancement -- supervised fine-tuning enables compact models to achieve comparable or superior performance to larger proprietary models, demonstrating the benchmark's value for developing robust MRAG systems The code is available at https://github.com/phycholosogy/VQQP_Bench
title Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation
topic Information Retrieval
url https://arxiv.org/abs/2602.13179