cs.CVNov 15, 2026

SAGE-VQA: A Training-Free, Self-Evolving Agentic Framework with Grounded Evidence for Knowledge-Based Visual Question Answering

Authors: Ruirui Shen, Jianqi Gao, Xiangfeng Luo, Yonggang Zhang, Muran Yu, Barney Haoyun Miao, Hang Yu, Yike Guo

Organizations: Shanghai University (shu.edu.cn) · The Hong Kong University of Science and Technology (ust.hk) · Stanford University (stanford.edu) · University of Calgary (ucalgary.ca)

Abstract

Knowledge-based visual question answering (KB-VQA) aims to combine visual information with external knowledge to answer user questions. Existing methods face two main bottlenecks: visual perception errors can propagate into hallucinations, and generalization across scenarios remains limited. To address these issues, we propose SAGE-VQA (Self-evolving Agent framework with Grounded Evidence), a training-free agentic framework that combines evidence verification with experience evolution. Our key insight is to explore an Evidence-Driven Adaptive Reasoning (EDAR) strategy. It accurately acquires and verifies question-relevant fine-grained visual information. It also extracts and refines reusable experience to support robust reasoning across tasks. Specifically, we design a Co-verified Visual Grounding module that verifies question-relevant visual information and provides grounded evidence for subsequent reasoning. We further introduce a Self-evolving Hierarchical Memory (SHM) mechanism. SHM organizes experiences into declarative and procedural memories based on their nature. These memories can be reused in subsequent reasoning and continually refined through feedback, without updating model parameters. Experimental results show that our method outperforms competing methods based on lightweight open-source vision-language models (VLMs) as well as those based on closed-source VLMs. Moreover, our method can serve as a plug-and-play reasoning framework for existing VLMs without modifying their architectures.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering

    Aug 22, 2026Long Shu, Shuochen Liu, Wei Chen +4Knowledge-Based Visual Question AnsweringMultimodal RAG

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

    Apr 8, 2026Zhuohong Chen, Zhenxian Wu, Yunyao Yu +6Visual Question AnsweringTool Use in VLMs

  3. Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering

    Apr 1, 2026Marco Morini, Sara Sarto, Marcella Cornia +2Knowledge-Based Visual Question AnsweringVLM Inference