Metraipolis › archive › dc_fca0d0e52065
VideoResearcher: Self-Improving Tool Design for Long-Video Understanding — arXiv:2609.19664
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19664
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:05:27.655Z
- SHA-256 of the archived text
4c243954887c0f6338ab09240fe72220db9d3c9cb8b0564f21805aee48b6ee86- Stable URL of this page
https://metraipolis.com/documento/dc_fca0d0e52065
How to cite
VideoResearcher: Self-Improving Tool Design for Long-Video Understanding — arXiv:2609.19664 — arXiv (en), https://arxiv.org/abs/2609.19664 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fca0d0e52065 (Metraipolis archive dc_fca0d0e52065, sha256 4c243954887c0f6338ab09240fe72220db9d3c9cb8b0564f21805aee48b6ee86)
BibTeX
@misc{dcfca0d0e52065,
title = {VideoResearcher: Self-Improving Tool Design for Long-Video Understanding — arXiv:2609.19664},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19664},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fca0d0e52065; sha256 4c243954887c0f6338ab09240fe72220db9d3c9cb8b0564f21805aee48b6ee86},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19664. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video agents have made substantial progress in long-video understanding. Yet effective video-agent systems require costly, time-consuming manual design and trial and error. Current self-improvement methods either refine low-impact prompts, recombine predefined micro-tools, or struggle with convergence in harness optimization. To bridge this gap, we target high-impact video-tool with VideoResearcher, a training-free multi-agent framework that autonomously designs, tests, and refines tools for video understanding, like a human researcher. VideoResearcher operates through dual Solving and Evolving loops: it analyzes tool-use trajectories to identify capability gaps, coordinates specialized agents to develop and validate executable tools, and reuses evolved tools to strengthen evidence acquisition in subsequent video reasoning. Through iterative tool refinement and validation, it progressively strengthens evidence acquisition without updating model parameters. VideoResearcher achieves state-of-the-art performance among self-improving agents and approaches the human-designed upper bound, demonstrating a training-free paradigm for long-video understanding that expands agent capabilities through autonomous tool development while reducing costly manual engineering. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.19664 — 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 2026-10-10T04:26:09.521Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).