# Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering

arXiv: https://arxiv.org/abs/2604.07146 · HTML: https://mlsanity.com/paper/2604.07146/

## Key facts

- Cited by 2 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 23 of its 35 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories](https://mlsanity.com/paper/2306.09224/) (2023)
- [Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs](https://mlsanity.com/paper/2404.15406/) (2024)
- [Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation](https://mlsanity.com/paper/2202.07654/) (2022)
- [Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent](https://mlsanity.com/paper/2411.02937/) (2024)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [EchoSight: Advancing Visual-Language Models with Wiki Knowledge](https://mlsanity.com/paper/2407.12735/) (2024)
- [VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents](https://mlsanity.com/paper/2504.09795/) (2025)
- [VideoQA in the Era of LLMs: An Empirical Study](https://mlsanity.com/paper/2408.04223/) (2024)
- [Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs](https://mlsanity.com/paper/2505.13026/) (2025)
- [Procedural Environment Generation for Tool-Use Agents](https://mlsanity.com/paper/2506.11045/) (2025)
- [Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering](https://mlsanity.com/paper/2510.14605/) (2025)
- [Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines](https://mlsanity.com/paper/2502.16641/) (2025)
- [SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs](https://mlsanity.com/paper/2406.19593/) (2024)
- [ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards](https://mlsanity.com/paper/2510.00568/) (2025)
- [Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition](https://mlsanity.com/paper/2601.11931/) (2026)
- [When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning](https://mlsanity.com/paper/2603.21289/) (2026)
- [R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation](https://mlsanity.com/paper/2602.00104/) (2026)
- [Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering](https://mlsanity.com/paper/2502.20964/) (2025)
- [Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering](https://mlsanity.com/paper/2504.04065/) (2025)

## Built on by (most cited first, 2 of 2)

- [DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents](https://mlsanity.com/paper/2608.18524/) (2026)
- [ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives](https://mlsanity.com/paper/2608.25531/) (2026)

## Abstract (arXiv)

Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods adopt a fixed pipeline that sequentially retrieves information, filters it, and then produces an answer. Such a design makes it difficult to adapt to diverse question types. Moreover, it separates retrieval from reasoning, making it hard for the model to decide when to search, how to refine queries, or when to stop. As a result, the retrieved evidence is often poorly aligned with the question. To address these limitations, we reformulate KB-VQA as a search-agent problem and model the solving process as a multi-step decision-making procedure. At each step, the agent selects one of four actions-Answer, Image Retrieval, Text Retrieval, and Caption-based on its current information state. We further design an automated pipeline to collect multi-step trajectories that record the agent's reasoning process, tool usage, and intermediate decisions. These trajectories are then used as supervision for fine-tuning. Experiments on InfoSeek and E-VQA demonstrate that our method achieves state-of-the-art performance, consistently outperforming prior baselines and confirming the effectiveness of our framework.