Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current approaches struggle at both ends: retrieval methods fail on complex, multi-faceted queries that cannot be captured by a single embedding, while generation methods lack the high-level reasoning needed to synthesize across multiple videos and face memory constraints over long, multi-video contexts. We present MARQUIS: a three-stage pipeline that addresses these limitations through (1) query expansion, fusion, and reranking, (2) calibrated structured evidence extraction, and (3) article generation from extracted evidence, optionally controlled by an RLM. On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems.
@article{arxiv.2605.17640,
title = {MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation},
author = {Debashish Chakraborty and Dengjia Zhang and Jialiang Jin and Hanting Liu and Katherine Guerrerio and Hanxiang Qin and Tyler Skow and Alexander Martin and Reno Kriz and Benjamin Van Durme},
journal= {arXiv preprint arXiv:2605.17640},
year = {2026}
}
Comments
Accepted as an oral presentation at the ACL 2026 Workshop MAGMaR Systems. 27 pages, 4 figures. Code can be found here: https://github.com/debashishc/marquis