# SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge

arXiv: https://arxiv.org/abs/2405.14554 · HTML: https://mlsanity.com/paper/2405.14554/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 35 of its 51 references that are in the map.
- First posted on arXiv 23 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [Retrieval-Augmented Multimodal Language Modeling](https://mlsanity.com/paper/2211.12561/) (2022)
- [REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory](https://mlsanity.com/paper/2212.05221/) (2022)
- [AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn](https://mlsanity.com/paper/2306.08640/) (2023)

## Built on by (most cited first, 20 of 20)

- [LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents](https://mlsanity.com/paper/2503.10200/) (2025)
- [DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search](https://mlsanity.com/paper/2510.12801/) (2025)
- [Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook](https://mlsanity.com/paper/2503.18016/) (2025)
- [VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning](https://mlsanity.com/paper/2506.06097/) (2025)
- [VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding](https://mlsanity.com/paper/2512.12360/) (2025)
- [QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models](https://mlsanity.com/paper/2510.16292/) (2025)
- [When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations](https://mlsanity.com/paper/2505.24449/) (2025)
- [FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models](https://mlsanity.com/paper/2407.11522/) (2024)
- [VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2511.19524/) (2025)
- [The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection](https://mlsanity.com/paper/2601.15316/) (2026)
- [GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory](https://mlsanity.com/paper/2511.12027/) (2025)
- [IA-T2I: Internet-Augmented Text-to-Image Generation](https://mlsanity.com/paper/2505.15779/) (2025)
- [WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models](https://mlsanity.com/paper/2604.02570/) (2026)
- [ROSE: Retrieval-Oriented Segmentation Enhancement](https://mlsanity.com/paper/2604.14147/) (2026)
- [DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation](https://mlsanity.com/paper/2606.00535/) (2026)
- [MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes](https://mlsanity.com/paper/2607.27798/) (2026)
- [Bringing The Consistency Gap: Explicit Structured Memory for Interleaved Image-Text Generation](https://mlsanity.com/paper/2510.10969/) (2025)
- [LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models](https://mlsanity.com/paper/2606.00573/) (2026)
- [GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory](https://mlsanity.com/paper/2606.06532/) (2026)
- [SocialBuddy: Tailoring Search Agent for Social Scenarios](https://mlsanity.com/paper/2609.01641/) (2026)

## Abstract (arXiv)

Large vision-language models (LVLMs) are ignorant of the up-to-date knowledge, such as LLaVA series, because they cannot be updated frequently due to the large amount of resources required, and therefore fail in many cases. For example, if a LVLM was released on January 2024, and it wouldn't know the singer of the theme song for the new Detective Conan movie, which wasn't released until April 2024. To solve the problem, a promising solution motivated by retrieval-augmented generation (RAG) is to provide LVLMs with up-to-date knowledge via internet search during inference, i.e., internet-augmented generation (IAG), which is already integrated in some closed-source commercial LVLMs such as GPT-4V. However, the specific mechanics underpinning them remain a mystery. In this paper, we propose a plug-and-play framework, for augmenting existing LVLMs in handling visual question answering (VQA) about up-to-date knowledge, dubbed SearchLVLMs. A hierarchical filtering model is trained to effectively and efficiently find the most helpful content from the websites returned by a search engine to prompt LVLMs with up-to-date knowledge. To train the model and evaluate our framework's performance, we propose a pipeline to automatically generate news-related VQA samples to construct a dataset, dubbed UDK-VQA. A multi-model voting mechanism is introduced to label the usefulness of website/content for VQA samples to construct the training set. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4V by about 25% in accuracy.