Metraipolis › archive › dc_97591fb92a06

VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research — arXiv:2610.04911

Source
arXiv
Original
https://arxiv.org/abs/2610.04911
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:52.970Z
SHA-256 of the archived text
d4f112f9462206e0e269405d51244a25e294b9056b39c748fb961592080bdc60
Stable URL of this page
https://metraipolis.com/documento/dc_97591fb92a06

How to cite

VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research — arXiv:2610.04911 — arXiv, https://arxiv.org/abs/2610.04911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97591fb92a06 (Metraipolis archive dc_97591fb92a06, sha256 d4f112f9462206e0e269405d51244a25e294b9056b39c748fb961592080bdc60)
BibTeX
@misc{dc97591fb92a06,
  title = {VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research — arXiv:2610.04911},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04911},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97591fb92a06; sha256 d4f112f9462206e0e269405d51244a25e294b9056b39c748fb961592080bdc60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that relevant videos are provided in advance. We study open-web video research, where an agent must autonomously discover relevant videos, navigate their temporal content, and ground answers in visual evidence. Training such agents at scale is challenging as live video interaction is slow and unreliable, whereas fixed local simulation can induce retrieval-specific shortcuts that fail to transfer to the open web. We introduce VideoResearchAgent, a scalable training framework to address these challenges. First, we introduce controllable task synthesis pipeline to synthesize multi-hop research tasks from timestamped visual evidence while filtering text-only shortcuts. Second, we build a field-aligned local video simulator that preserves deployment-facing search and watch interactions while accelerating video search by a factor of 34.5-64.6. Third, we introduce Retrieval-Domain-Randomized GRPO (RDR-GRPO), which diversifies candidate rankings, distractors, metadata, and result structure during training to reduce overfitting to simulated retrieval. On Video-BrowseComp, the VideoResearchAgent trained using Qwen3.5-4B achieves 40.48% accuracy, comparable to Gemini-3-Flash-Preview, while reducing cumulative API-token consumption by 74.9% relative to the untrained model. Together, these results establish an accurate and efficient training recipe for open-web video research.

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/2610.04911 — 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 2026-10-06T05:24:05.532Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).