Metraipolis › archive › dc_f97fcca9eb2e

Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos — arXiv:2608.26355

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26355
License (as archived)
CC0-1.0
Archived
2026-10-17T16:15:43.082Z
SHA-256 of the archived text
8db77bee3dc8daaec8cf76bbd50ef04da34a6269090c536822e9e63cca8f6a43
Stable URL of this page
https://metraipolis.com/documento/dc_f97fcca9eb2e

How to cite

Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos — arXiv:2608.26355 — arXiv (en), https://arxiv.org/abs/2608.26355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f97fcca9eb2e (Metraipolis archive dc_f97fcca9eb2e, sha256 8db77bee3dc8daaec8cf76bbd50ef04da34a6269090c536822e9e63cca8f6a43)
BibTeX
@misc{dcf97fcca9eb2e,
  title = {Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos — arXiv:2608.26355},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26355},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f97fcca9eb2e; sha256 8db77bee3dc8daaec8cf76bbd50ef04da34a6269090c536822e9e63cca8f6a43},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often fails to provide cues that discriminate the correct answer from plausible alternatives. Diagnostic analysis on a manually annotated subset of MMR-V shows that prior agentic systems substantially improve cue retrieval over direct VLM inference yet fail to achieve a corresponding gain in answer accuracy, indicating that the bottleneck lies in option-discriminative evidence rather than topical relevance alone. We propose PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition. PACE proceeds in two stages: it first indexes clip-level descriptions guided by question-derived factors without observing the candidate answers; it then uses the candidate answers to derive contrastive cues and queries the index for verification. On MMR-V with the open-source Qwen3-VL backbone, PACE achieves 42.6% accuracy, outperforming direct inference and prior agentic baselines including Deep Video Discovery (DVD). On the same diagnostic subset, PACE recovers 66.9% of the annotated cues, providing empirical evidence that its gains are associated with improved evidence recovery rather than stronger answer-side priors alone. Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.26355 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:34:49.983Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).