SOURCE-LINKED INTELLIGENCE
VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning
Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language models to vision-language models (VLMs) introduces a distinct state-management problem. Visual reasoning produces intermediate image-valued evidence---crops, masks, overlays, zoomed regions, and analytic renderings---that must remain addressable without accumulating unboundedly in multimodal context. We introduce VLM-in-Sandbox, a training-free framework for agentic multimodal reasoning in controlled computer environments. Its Visual Workspace re
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-21T09:52:48.000Z
First collected: 2026-09-23T08:01:43.213Z. This is not the publication date.