ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding

Computer Science > Artificial Intelligence [Submitted on 29 Jul 2026] ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding Xinkui Zhao, Enbo Chen, Yifan Zhang, Chang Liu, Guanjie Cheng, Naibo Wang, Yueshen Xu Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to entity confusion, error propagation, and hallucinated answers. We propose ViSAGE, a multimodal agentic memory framework that constructs self-correcting, entity-centric memories. Specifically, ViSAGE anchors entity identity via cross-modal binding over long temporal ranges. It then applies bidirectional memory refinement to propagate delayed identity evidence, retroactively unifying historical records and improving future reasoning. We also introduce multi-agent cross-verification to assess retrieved evidence under an identity-evidence alignment onstraint, enabling abstention instead of unsupported answers when evidence is missing. Extensive results demonstrate that ViSAGE consistently outperforms the strongest baseline, achieving 5.9% higher accuracy. Comments: Accept by ACMMM 2026 Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2607.28678 [cs.AI]   (or arXiv:2607.28678v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2607.28678 Focus to learn more Related DOI: https://doi.org/10.1145/3767308.3835852 Focus to learn more Submission history From: Yifan Zhang [view email] [v1] Wed, 29 Jul 2026 10:25:23 UTC (942 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-07 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)