# Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation

arXiv: https://arxiv.org/abs/2606.05268 · HTML: https://mlsanity.com/paper/2606.05268/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 98 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting](https://mlsanity.com/paper/2402.07207/) (2024)
- [TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation](https://mlsanity.com/paper/2410.03608/) (2024)
- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes](https://mlsanity.com/paper/2602.09153/) (2026)
- [BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement](https://mlsanity.com/paper/2412.14203/) (2024)
- [ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary](https://mlsanity.com/paper/2506.00742/) (2025)
- [iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs](https://mlsanity.com/paper/2502.03214/) (2025)
- [FlairGPT: Repurposing LLMs for Interior Designs](https://mlsanity.com/paper/2501.04648/) (2025)
- [Shrinking the Generation-Verification Gap with Weak Verifiers](https://mlsanity.com/paper/2506.18203/) (2025)
- [Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach](https://mlsanity.com/paper/2411.14484/) (2024)
- [Do 3D Large Language Models Really Understand 3D Spatial Relationships?](https://mlsanity.com/paper/2603.23523/) (2026)
- [TextLap: Customizing Language Models for Text-to-Layout Planning](https://mlsanity.com/paper/2410.12844/) (2024)

## Built on by (most cited first, 1 of 1)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)

## Abstract (arXiv)

We present a pipeline for building and aggregating task-specific, LLM-generated weak (imperfect) verifiers into a strong verifier for spatial layout domains. Given a task description, our pipeline asks an LLM to synthesize a collection of verifier programs using a layout verification DSL. Each individual LLM-generated verifier usually provides an imperfect check for a match between the layout and the corresponding task description. We show that by aggregating the responses of many such verifiers we can produce a stronger verifier. Moreover, by applying techniques from weak learning, our pipeline can learn how to aggregate the weak verifiers from a very sparse set of human labeled example layouts (about 10). We find that the strong verifiers produced by our pipeline outperform the status-quo approach of using a set of LLM judges to directly check whether a layout matches a task description, raising F1-scores by up to 7X across a variety of 3D room layout and 2D poster design tasks. We also demonstrate that verifier-guided layout generation using natural language feedback from our strong verifiers improves layout quality of a base layout generator by up to 66.2% according to a human evaluator.