world model for agents
A predictive environment model that agents use to simulate outcomes, enabling planning, reasoning, and long-horizon task execution.
- Papers
- 7
- Released code
- 1
- First seen
- Aug 2026
- Latest
- Sept 2026
7 papers in the last two months, against 0 in the two before.
The papers
Most central to this idea first, not most recent.
- Big Techcs.LG
Predicting environment observations during fine-tuning improves later agent exploration
University of Maryland, AWS AI Labs · Sept 2026
- Chinese Techcs.CV
Executable code gives generative worlds persistent rules and evolving state
USTC, TongYi Lab · Sept 2026
- Research Labcs.CV
Adding Depth Helps Video World Models Control Robots More Reliably
Inria, École Normale Supérieure · Sept 2026
- Top Universitycs.ROcode
One video world model transfers physical dynamics across robot bodies
Princeton University · Aug 2026
- Industrycs.CL
Editing agent reasoning history boosts long-horizon task performance
Gaoling School of Artificial Intelligence, Renmin University of China · Sept 2026
- Independentcs.AI
Scene-grounded decoding keeps vision-language plans executable and visually supported
Sept 2026
- Chinese Techcs.CV
Language enables precise character and camera control in video worlds
Tencent, National University of Singapore · Sept 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.