Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Not provided in the content

executable representationsphysical reasoningmultimodalagentic discovery

2608.27549

Builder Relevance

80%

2h ago

Abstract

This work introduces Code-as-World, a paradigm for representing physical worlds through executable world representations to enhance physical reasoning.

Reality Card

Core Claim

Code-as-World provides a scalable foundation for physical intelligence by achieving state-of-the-art performance on quantitative physical reasoning tasks.

Method / Result

Code-as-World-VL surpasses leading proprietary models on the QuantiPhy benchmark.

Limitations

The paper does not specify the authors or provide detailed experimental setups, which may hinder reproducibility.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers