# ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

arXiv: https://arxiv.org/abs/2606.27974 · HTML: https://mlsanity.com/paper/2606.27974/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 33 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [DeepEyesV2: Toward Agentic Multimodal Model](https://mlsanity.com/paper/2511.05271/) (2025)
- [MMSearch-R1: Incentivizing LMMs to Search](https://mlsanity.com/paper/2506.20670/) (2025)
- [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)
- [EchoSight: Advancing Visual-Language Models with Wiki Knowledge](https://mlsanity.com/paper/2407.12735/) (2024)
- [SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning](https://mlsanity.com/paper/2512.24330/) (2025)
- [MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts](https://mlsanity.com/paper/2502.20808/) (2025)
- [Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2411.16863/) (2024)
- [MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework](https://mlsanity.com/paper/2504.10074/) (2025)
- [Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering](https://mlsanity.com/paper/2510.14605/) (2025)
- [OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval](https://mlsanity.com/paper/2505.07879/) (2025)
- [CompCap: Improving Multimodal Large Language Models with Composite Captions](https://mlsanity.com/paper/2412.05243/) (2024)
- [ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2511.22715/) (2025)
- [EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability](https://mlsanity.com/paper/2503.10042/) (2025)
- [QKVQA: Question-Focused Filtering for Knowledge-based VQA](https://mlsanity.com/paper/2601.13856/) (2026)
- [CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2602.23952/) (2026)

## Built on by (most cited first, 5 of 5)

- [DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents](https://mlsanity.com/paper/2608.18524/) (2026)
- [SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling](https://mlsanity.com/paper/2609.34502/) (2026)
- [Memory-Conditioned Tool Calling for Camera-First Visual Agents](https://mlsanity.com/paper/2607.09822/) (2026)
- [LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search](https://mlsanity.com/paper/2608.09152/) (2026)
- [ActICL: Post-Training for Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2610.19475/) (2026)

## Abstract (arXiv)

Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pipeline with a pre-selected retriever and a static top-k setting, which is not adaptive during reasoning. We propose ProMSA, a progressive multimodal search agent for KB-VQA. Given an image-question pair, the agent iteratively chooses image search, text search, or stop, under explicit tool-call budgets and with deduplication to avoid redundant retrieval. For training, we first use rejection-sampling SFT to learn valid tool-use formats, then optimize the agent with TN-GSPO, a sequence-level RL objective that normalizes updates by both generation length and tool-interaction depth. Experiments on E-VQA and InfoSeek show consistent gains over strong RAG and agent baselines, and improved retrieval and end-to-end accuracy. The code is available at https://github.com/DingWu1021/Promsa.