Metraipolis › archive › dc_fe65d9f7dbf6
VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding — arXiv:2610.01766
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01766
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:06:02.905Z
- SHA-256 of the archived text
2afcef79ad4bf9cb26bd93d5292f0ffcc790a2e793411d47a98bec390635ea99- Stable URL of this page
https://metraipolis.com/documento/dc_fe65d9f7dbf6
How to cite
VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding — arXiv:2610.01766 — arXiv (en), https://arxiv.org/abs/2610.01766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe65d9f7dbf6 (Metraipolis archive dc_fe65d9f7dbf6, sha256 2afcef79ad4bf9cb26bd93d5292f0ffcc790a2e793411d47a98bec390635ea99)
BibTeX
@misc{dcfe65d9f7dbf6,
title = {VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding — arXiv:2610.01766},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01766},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe65d9f7dbf6; sha256 2afcef79ad4bf9cb26bd93d5292f0ffcc790a2e793411d47a98bec390635ea99},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video temporal grounding aims to localize events in videos from natural-language queries. For agents built around frozen video-language models, the harness determines how queries guide temporal predictions and how those predictions are refined. Manually refining these harnesses requires diagnosing grounding failures and coordinating changes to both agent workflows and instructions. We introduce VideoEvolve, a framework that automatically evolves agent harnesses for video temporal grounding. VideoEvolve uses a Cloze-Structured Harness Representation that preserves stage interfaces while leaving agent workflows and instructions open to evolution. Branch-Guided Harness Evolution preserves promising code branches for continued refinement, using execution feedback to guide local edits and validation to determine which improvements are carried forward. Experiments demonstrate improved grounding performance across multiple benchmarks. Component analyses identify instruction refinement as a consistent source of gains, while the benefits of evolved code vary across evaluation settings. Together, these results support automated harness evolution as an effective approach to improving video temporal grounding. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.01766 — 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 2026-10-06T10:21:27.972Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).