An agentic mRAG framework uses GRPO-trained visual reranking and active rejection to verify retrieved candidate entities, achieving state-of-the-art on three KB-VQA benchmarks.
Knowledge-based visual question answering with multimodal processing, retrieval, and filtering
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Audit of KB-VQA benchmarks reveals systematic violations of answer derivability, question clarity, and visual disambiguation assumptions, with new repair and multi-entity augmentation protocols producing different model performance trends.
ProMSA is a progressive multimodal search agent for KB-VQA that iteratively selects search tools under budgets, trained via rejection-sampling SFT then TN-GSPO RL, reporting gains on E-VQA and InfoSeek over RAG baselines.
MetaRA applies metamorphic testing to VQA tasks and shows that MLLM models exhibit sensitivity to linguistic perturbations and superficial visual cues not detected by conventional accuracy benchmarks.
A new CoVQD-guided retrieval-augmented generation framework improves multimodal LLMs on visual question answering by using structured reasoning to retrieve better external knowledge.
citing papers explorer
-
MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG
An agentic mRAG framework uses GRPO-trained visual reranking and active rejection to verify retrieved candidate entities, achieving state-of-the-art on three KB-VQA benchmarks.
-
Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting
Audit of KB-VQA benchmarks reveals systematic violations of answer derivability, question clarity, and visual disambiguation assumptions, with new repair and multi-entity augmentation protocols producing different model performance trends.
-
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering
ProMSA is a progressive multimodal search agent for KB-VQA that iteratively selects search tools under budgets, trained via rejection-sampling SFT then TN-GSPO RL, reporting gains on E-VQA and InfoSeek over RAG baselines.
-
MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems
MetaRA applies metamorphic testing to VQA tasks and shows that MLLM models exhibit sensitivity to linguistic perturbations and superficial visual cues not detected by conventional accuracy benchmarks.
-
Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation
A new CoVQD-guided retrieval-augmented generation framework improves multimodal LLMs on visual question answering by using structured reasoning to retrieve better external knowledge.