# Look, Reason, Draw a Region: Recursive Refinement for Spatial Context Prediction

Authors: Wajeeha Tahir, Anna Tegon, Lionnus Kesting, Gamze İslamoğlu, Kristóf Karacs, Luca Benini, Thorir Mar Ingolfsson.

Repeatedly updates hidden reasoning and answer states from image features and a spatial-language prompt using a shared transformer. Decodes the refined answer state into a convex region mask and compares it with a single-step model.

First public: 2026-10-16.
ArXiv initial submission: 2026-10-16.

[Original paper](https://arxiv.org/abs/2610.23302) · [PDF](https://arxiv.org/pdf/2610.23302) · [HTML](https://arxiv.org/html/2610.23302v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.23302/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.23302/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.23302/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.23302/record.json)

## Approaches

- [Recurrent reasoning](https://latent-implicit-thinking.github.io/topics/recurrent-reasoning/): Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.

Reading-list version 0.11.0; literature checked through 2026-10-26.