# Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search

arXiv: https://arxiv.org/abs/2510.16147 · HTML: https://mlsanity.com/paper/2510.16147/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2025.

## Built on by (most cited first, 10 of 10)

- [Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal](https://mlsanity.com/paper/2602.04053/) (2026)
- [SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation](https://mlsanity.com/paper/2604.27555/) (2026)
- [HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents](https://mlsanity.com/paper/2606.09738/) (2026)
- [ShellMaker: Language-Guided Exterior Completion under Structural Constraints](https://mlsanity.com/paper/2606.31680/) (2026)
- [CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling](https://mlsanity.com/paper/2604.27361/) (2026)
- [aDSL: Agentic 3D Creation via Joint Agent-Program Design](https://mlsanity.com/paper/2608.17975/) (2026)
- [ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python](https://mlsanity.com/paper/2604.26943/) (2026)
- [Text2Sim: Agentic Physics-Based Simulation Generation with Distilled Expertise](https://mlsanity.com/paper/2609.36593/) (2026)
- [VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs](https://mlsanity.com/paper/2610.13145/) (2026)
- [Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation](https://mlsanity.com/paper/2610.15290/) (2026)

## Abstract (arXiv)

Synthesizing 3D scenes from open-vocabulary text descriptions is a challenging, important, and recently-popular application. One of its critical subproblems is layout generation: given a set of objects, lay them out to produce a scene matching the input description. Nearly all recent work adopts a declarative paradigm for this problem: using an LLM to generate a specification of constraints between objects, then solving those constraints to produce the final layout. In contrast, we explore an alternative imperative paradigm, in which an LLM iteratively places objects, with each object's position and orientation computed as a function of previously-placed objects. The imperative approach allows for a simpler scene specification language while also handling a wider variety and larger complexity of scenes. We further improve the robustness of our imperative scheme by developing an error correction mechanism that iteratively improves the scene's validity while staying as close as possible to the original layout generated by the LLM. In forced-choice perceptual studies, participants preferred layouts generated by our imperative approach 82% and 94% of the time when compared against two declarative layout generation methods. We also present a simple, automated evaluation metric for 3D scene layout generation that aligns well with human preferences.