Metraipolis › archive › dc_1faa0eb6efe6
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness — arXiv:2610.21910
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21910
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:04:06.427Z
- SHA-256 of the archived text
36fde23f3b07b73596f6a3eb3960e20e50434eb8659e538319cc0537b932e3a9- Stable URL of this page
https://metraipolis.com/documento/dc_1faa0eb6efe6
How to cite
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness — arXiv:2610.21910 — arXiv (en), https://arxiv.org/abs/2610.21910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1faa0eb6efe6 (Metraipolis archive dc_1faa0eb6efe6, sha256 36fde23f3b07b73596f6a3eb3960e20e50434eb8659e538319cc0537b932e3a9)
BibTeX
@misc{dc1faa0eb6efe6,
title = {CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness — arXiv:2610.21910},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21910},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1faa0eb6efe6; sha256 36fde23f3b07b73596f6a3eb3960e20e50434eb8659e538319cc0537b932e3a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over motion, actions, and view changes beyond what the input images show. Video World Models (VWMs) provide a natural unified engine for visual imagination by generating task-relevant visual content as additional evidence. However, existing approaches typically invoke a VWM through fixed pipelines centered on a predefined form of visual imagination, such as novel-view synthesis. To support flexible visual imagination for diverse reasoning tasks, we introduce CoWorld Reasoner, an agentic framework that uses a VWM as a unified visual reasoning engine. Its Video World Model-Driven Harness exposes multiple visual operations through tools and uses skills to guide the VLM in deciding whether to imagine, selecting an operation, constructing a generation request, and interpreting the resulting visual evidence. We further introduce VLM-VWM Harness Co-Evolution, which jointly revises tools, skills, and execution code based on execution feedback while keeping both model weights fixed. Across seven benchmarks spanning spatial intelligence, temporal and causal reasoning, and perceptual reasoning, CoWorld Reasoner outperforms direct reasoning with the same VLM. The strongest variant improves on all seven benchmarks, including relative accuracy gains of 11.8% on MMSI and 13.0% on ERQA, and outperforms all five evolving baselines using the same backbone across five benchmarks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.21910 — 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 2026-10-16T08:44:17.798Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).