Code as Worlds: Agentic Discovery of Executable World Representations
_akhaliq · x · 2026-08-31
The paper "Code as Worlds" introduces code as executable representations for the physical world and an agentic process to discover them through iterative simulation and verification. This approach transforms raw observations into reusable physical data—explicit states, dynamics, and mechanisms—capturing not only what was seen but the underlying world that produced it. It provides scalable physical supervision, enabling state-of-the-art performance on quantitative physical reasoning benchmarks.
Related event: Code-as-World: Representing Physical Worlds as Executable Code(3 posts)→
More from Research
- Interpretability debate: one interpretable polysemantic neuron doesn't prove all are — aran_nayebi · 2026-10-16
- Optuna creator Akiba: when 2 hyperparameters cost $20M, what's left for BO/HPO — Stefania_druga · 2026-10-16
- AI will be superhuman at science regardless, and Europe can't opt out — teortaxesTex · 2026-10-16
- SERO augments long-horizon agentic RL with executable oracle continuations — Shanghai-AI-Laboratory · 2026-10-16
- Tsinghua and Amap propose OmniVerifier-C1, a graded verifier beating binary judges — Bowei Liu · 2026-10-16
- Alibaba open-sources MAI-Gym, an all-in-one GUI agent eval and RL training platform — Tongyi-MAI · 2026-10-16