Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
- Published
- Source
- arXiv
- Paper number
- 1049
- Field
- Computer Vision
- arXiv ID
- 2608.27549
Key points
- It encoded objects, physical laws, and appearance as code to create compact world representations that can also be verified numerically.
- An agent loop of proposal, execution, rendering, verification, and revision, inspired by abductive reasoning, automatically discovered world representations from text or video.
- Using verified executable worlds as supervision, it taught vision-language models quantitative physical reasoning, such as answering questions about speed or mass in videos.
- Code-as-World-VL-9B outperformed much larger commercial models such as Gemini-3.1-Flash on QuantiPhy, while the 27B model achieved the best overall score.
- Its central contribution is translating the scientific discovery process of forming hypotheses and testing them experimentally into an agent loop.
Paper links
External research summaries. These are not HDATF publications or measured product results.