# New framework builds reusable visual planners from a single scene

> Researchers show a training‑free method that creates planning programs with 99.3% success after one practice scene.

Oossa · 2026-10-16 · https://oossa.com/en/new-framework-builds-reusable-visual-planners-from-a-single-scene

Ruixiao Yang and co‑authors released a paper on Oct 15, 2026 describing a training‑free framework that builds reusable perception and planning programs from a single practice scene. The system uses a vision‑language model’s rendering ability to check its own actions and refine the program without any solution labels. After refinement, the frozen program solves new instances without further calls to the large model. Tests on fifteen 2D and 3D domains showed an average planning success rate of 99.3%.

## The facts

- 99.3% average planning success across 15 domain variants
- Paper published Oct 15, 2026 ("Tue, 13 Oct 2026 21:52:22 UTC" submission; listed date "Thu Oct 15 2026")

## Why it matters

It lets developers create visual planning systems with far lower compute cost, making AI‑driven automation more practical for robotics and simulation.

## Sources & references

1. [Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene](https://arxiv.org/abs/2610.19234) – arXiv, 2026-10-15

Last updated: 2026-10-16