Metraipolis › archive › dc_29fa16de4269

CASE: Cost-Aware Stopping for Efficient Long-Video Agents — arXiv:2610.05400

Source
arXiv
Original
https://arxiv.org/abs/2610.05400
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:09.736Z
SHA-256 of the archived text
9ce0f3092a11b5a7b71e498ed893ed4c32aa940e262f5f06aa123d44eaf8d09a
Stable URL of this page
https://metraipolis.com/documento/dc_29fa16de4269

How to cite

CASE: Cost-Aware Stopping for Efficient Long-Video Agents — arXiv:2610.05400 — arXiv, https://arxiv.org/abs/2610.05400 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29fa16de4269 (Metraipolis archive dc_29fa16de4269, sha256 9ce0f3092a11b5a7b71e498ed893ed4c32aa940e262f5f06aa123d44eaf8d09a)
BibTeX
@misc{dc29fa16de4269,
  title = {CASE: Cost-Aware Stopping for Efficient Long-Video Agents — arXiv:2610.05400},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05400},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29fa16de4269; sha256 9ce0f3092a11b5a7b71e498ed893ed4c32aa940e262f5f06aa123d44eaf8d09a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05400. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough to answer? We propose CASE, a plug-in termination framework that frames this decision as policy-conditioned sequential stopping. At each causal checkpoint, CASE combines an auxiliary multiple-choice assessment of accumulated evidence with the host agent's execution state. From complete native trajectories, we construct a cost-aware target that compares answering now with stopping later along the same search path, accounting jointly for answer correctness and the full cost of continued reasoning. A lightweight Ridge regressor learns this decision gap and produces STOP/CONTINUE decisions. We evaluate three vision-language models with VideoSeek and AVP. On Video-MME, end-to-end accuracy changes by +0.67 percentage points on average while CASE reduces model-token use by 53.63%. The same frozen policies then transfer zero-shot to LongVideoBench and MLVU, with end-to-end accuracy changes of +3.38 and +4.58 points while saving 58.78% and 51.28% of model tokens, respectively. Across all agent-model-benchmark combinations, CASE attains the highest accuracy-efficiency Pareto-frontier coverage among the compared stopping methods (83.3%) at the selected operating points. Online execution preserves this favorable accuracy-efficiency trade-off and additionally reduces measured runtime by 54.1% on average. CASE provides a plug-in termination framework for long-video reasoning agents, enabling them to decide when further evidence acquisition is no longer worthwhile.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.05400 — 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 2026-10-06T05:24:05.585Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).