Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation

Abstract:This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR). Addressing the critical challenges of cross-lingual long-video comprehension, strict persona adherence, and zero-hallucination temporal grounding, we propose a fully training-free, two-stage cascaded Video RAG pipeline. Our architecture strategically decouples semantic retrieval from cognitive logical reasoning through a modality-aware division of labor. In the first stage, a high-recall semantic pre-fetching module employs dense retrieval using only high-fidelity visual summaries and global text descriptions, explicitly isolating noisy modalities (e.g., OCR and ASR) to maintain a pristine vector space. In the second stage, an Adaptive, Iterative, and Reasoning-based (A.I.R.) filtering agent, powered by a commercial Large Language Model (LLM), performs fine-grained cognitive reranking. The agent re-incorporates full multimodal contexts to enforce strict logical alignment with user personas, effectively pruning semantically similar but logically irrelevant candidates. Finally, a Prompt Sculpting mechanism constrains the generator to synthesize the distilled subset into strictly formatted JSON responses with exact chunk-level citations. Evaluated on the RAG track, our resource-aware approach shows exceptional precision in both information retrieval and persona-conditioned generation.

To be presented at ACL 2026 MAGMAR Workshop (Oral; Retrieval leaderboard No.1)

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multimedia (cs.MM)

arXiv:2606.07924 [cs.CV]

(or arXiv:2606.07924v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.07924 arXiv-issued DOI via DataCite (pending registration)