Multimodal Iterative RAG for Knowledge-Intensive Visual Question Answering

• URL: http://arxiv.org/abs/2509.00798v4
• Date: Mon, 29 Sep 2025 13:50:38 GMT
• Title: Multimodal Iterative RAG for Knowledge-Intensive Visual Question Answering
• Authors: Changin Choi, Wonseok Lee, Jungmin Ko, Wonjong Rhee,
• Abstract summary: We propose MI-RAG, a framework that leverages reasoning to enhance retrieval and incorporates knowledge synthesis to refine its understanding.<n>Experiments on challenging benchmarks, including Encyclopedic VQA, InfoSeek, and OK-VQA, show that MI-RAG significantly improves both retrieval recall and answer accuracy.
• Score: 8.830228556155673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in Multimodal Large Language Models~(MLLMs) have significantly enhanced the ability of these models in multimodal understanding and reasoning. However, the performance of MLLMs for knowledge-intensive visual questions, which require external knowledge beyond the visual content of an image, still remains limited. While Retrieval-Augmented Generation (RAG) has become a promising solution to provide models with external knowledge, its conventional single-pass framework often fails to gather sufficient knowledge. To overcome this limitation, we propose MI-RAG, a Multimodal Iterative RAG framework that leverages reasoning to enhance retrieval and incorporates knowledge synthesis to refine its understanding. At each iteration, the model formulates a reasoning-guided multi-query to explore multiple facets of knowledge. Subsequently, these queries drive a joint search across heterogeneous knowledge bases, retrieving diverse knowledge. This retrieved knowledge is then synthesized to enrich the reasoning record, progressively deepening the model's understanding. Experiments on challenging benchmarks, including Encyclopedic VQA, InfoSeek, and OK-VQA, show that MI-RAG significantly improves both retrieval recall and answer accuracy, establishing a scalable approach for compositional reasoning in knowledge-intensive VQA.

Related papers

• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• mKG-RAG: Multimodal Knowledge Graph-Enhanced RAG for Visual Question Answering [29.5761347590239]
  Retrieval-Augmented Generation (RAG) has been proposed to expand internal knowledge of Multimodal Large Language Models (MLLMs)<n>In this paper, we propose a novel multimodal knowledge-augmented generation framework (mKG-RAG) based on multimodal KGs for knowledge-intensive VQA tasks.
  arXiv  Detail & Related papers  (2025-08-07T12:22:50Z)
• DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router [57.28685457991806]
  DeepSieve is an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router.<n>Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design.
  arXiv  Detail & Related papers  (2025-07-29T17:55:23Z)
• Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown [22.543774418924226]
  multimodal large language models (MLLMs) often fail in rarely encountered domain-specific tasks due to limited relevant knowledge.<n>We construct a multimodal knowledge graph (MH-MMKG) which incorporates multi-modalities and intricate entity relations.<n>We also design a series of challenging queries based on MH-MMKG to evaluate the models' ability for complex knowledge retrieval and reasoning.
  arXiv  Detail & Related papers  (2025-06-21T05:01:02Z)
• Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger [51.01841635655944]
  Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks.<n>Existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge.<n>We propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method.
  arXiv  Detail & Related papers  (2025-06-09T14:00:57Z)
• CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG [53.950029990391066]
  Cross-source knowledge textbfReconciliation for Multimodal RAG (CoRe-MMRAG)<n>We propose a novel end-to-end framework that effectively reconciles inconsistencies across knowledge sources.<n>Experiments on KB-VQA benchmarks show that CoRe-MMRAG achieves substantial improvements over baseline methods.
  arXiv  Detail & Related papers  (2025-06-03T07:32:40Z)
• Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation [77.10390725623125]
  retrieval-augmented generation (RAG) is widely employed to expand their knowledge scope.<n>Since RAG has shown promise in knowledge-intensive tasks like open-domain question answering, its broader application to complex tasks and intelligent assistants has further advanced its utility.<n>We present a systematic investigation of the intrinsic mechanisms by which RAGs integrate internal (parametric) and external (retrieved) knowledge.
  arXiv  Detail & Related papers  (2025-05-17T13:13:13Z)
• OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval [17.75545831558775]
  Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA)<n>We propose a multimodal RAG system featuring a coarse-to-fine, multi-step retrieval that harmonizes multiple granularities and modalities to enhance efficacy.
  arXiv  Detail & Related papers  (2025-05-10T14:24:41Z)
• Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations [65.11348389219887]
  We introduce Dialectic-RAG (DRAG), a modular approach that evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives.<n>We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models.
  arXiv  Detail & Related papers  (2025-04-07T06:55:15Z)
• A Survey of Multimodal Retrieval-Augmented Generation [3.9616308910160445]
  Multimodal Retrieval-Augmented Generation (MRAG) enhances large language models (LLMs) by integrating multimodal data (text, images, videos) into retrieval and generation processes.<n>Recent studies show MRAG outperforms traditional Retrieval-Augmented Generation (RAG) in scenarios requiring both visual and textual understanding.
  arXiv  Detail & Related papers  (2025-03-26T02:43:09Z)
• Open-Ended and Knowledge-Intensive Video Question Answering [20.256081440725353]
  We investigate knowledge-intensive video question answering (KI-VideoQA) through the lens of multi-modal retrieval-augmented generation.<n>Our analysis examines various retrieval augmentation approaches using cutting-edge retrieval and vision language models.<n>We achieve a substantial 17.5% improvement in accuracy on multiple choice questions in the KnowIT VQA dataset.
  arXiv  Detail & Related papers  (2025-02-17T12:40:35Z)
• mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA [78.45521005703958]
  multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge. We propose a novel framework called textbfRetrieval-textbfReftextbfAugmented textbfGeneration (mR$2$AG) which achieves adaptive retrieval and useful information localization. mR$2$AG significantly outperforms state-of-the-art MLLMs on INFOSEEK and Encyclopedic-VQA
  arXiv  Detail & Related papers  (2024-11-22T16:15:50Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
  We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning) The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs. It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-31T14:23:49Z)
• Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation [10.431782420943764]
  This paper introduces a novel multi-view RAG framework, MVRAG, tailored for knowledge-dense domains. Experiments conducted on legal and medical case retrieval demonstrate significant improvements in recall and precision rates.
  arXiv  Detail & Related papers  (2024-04-19T13:27:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.