Official Repository for NeurIPS'25 Paper "Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task"
A modular framework for benchmarking multimodal AI agents in a reproducible, full-OS environment. Using and adaption of the Smolagents's CodeAgent, Docker containers to run the VM in, VM's created using Qemu.
Fully local AI desktop application that uses multi-agent orchestration to analyze short videos (~1 min) through natural language queries. All AI inference runs offline with no cloud dependencies.
Evaluation of GPT-4o-mini on OSWorld desktop automation benchmark. Compares screenshot-only vs accessibility tree-enhanced approaches across 10 tasks (Chrome, LibreOffice, file ops, etc). Documents critical coordinate extraction failures and provides architectural recommendations for GUI agents.
Add a description, image, and links to the multimodal-agents topic page so that developers can more easily learn about it.
To associate your repository with the multimodal-agents topic, visit your repo's landing page and select "manage topics."