World Intelligence Agent: Unifying World Modeling and Action Learning for Digital Agents
Darwin Agent Team | Technical Report / Preprint
Read the report
Overview
World Intelligence Agent (WIA) unifies world modeling and action learning for digital agents. The report introduces WIA-Corpus and WIA-Bench, presents the WIA-WM family of world models, and explores simulation-based training, inference lookahead, and the WIA-WAM extension for action generation.
Please refer to the full report for the methods, experimental protocols, results, and limitations.
This repository hosts the technical report only; it does not contain model weights or executable code.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support