# InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity

arXiv: https://arxiv.org/abs/2511.18200 · HTML: https://mlsanity.com/paper/2511.18200/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 68 references that are in the map.
- First posted on arXiv 22 Nov 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 23 of 23)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models](https://mlsanity.com/paper/2506.03135/) (2025)
- [Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas](https://mlsanity.com/paper/2503.01773/) (2025)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent](https://mlsanity.com/paper/2509.20414/) (2025)
- [How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective](https://mlsanity.com/paper/2509.18905/) (2025)
- [SynCity: Training-Free Generation of 3D Worlds](https://mlsanity.com/paper/2503.16420/) (2025)
- [Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.19707/) (2025)
- [Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning](https://mlsanity.com/paper/2506.05341/) (2025)
- [WorldGrow: Generating Infinite 3D World](https://mlsanity.com/paper/2510.21682/) (2025)
- [SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding](https://mlsanity.com/paper/2511.04668/) (2025)
- [VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling](https://mlsanity.com/paper/2503.15855/) (2025)
- [LUMINOUS: Indoor Scene Generation for Embodied AI Challenges](https://mlsanity.com/paper/2111.05527/) (2021)
- [GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes](https://mlsanity.com/paper/2505.20294/) (2025)
- [ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment](https://mlsanity.com/paper/2507.19058/) (2025)
- [ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing](https://mlsanity.com/paper/2506.02459/) (2025)
- [Camera Trajectory Generation: A Comprehensive Survey of Methods, Metrics, and Future Directions](https://mlsanity.com/paper/2506.00974/) (2025)
- [A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design](https://mlsanity.com/paper/2303.04315/) (2023)

## Built on by (most cited first, 5 of 5)

- [LychSim: A Controllable and Interactive Simulation Framework for Vision Research](https://mlsanity.com/paper/2605.12449/) (2026)
- [MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation](https://mlsanity.com/paper/2602.07082/) (2026)
- [Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models](https://mlsanity.com/paper/2605.07148/) (2026)
- [ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python](https://mlsanity.com/paper/2604.26943/) (2026)
- [SABRE: Scalable and Automated Benchmarking of VLMs under Stress](https://mlsanity.com/paper/2608.07435/) (2026)

## Abstract (arXiv)

Modern vision-language models (VLMs) are expected to have abilities of spatial reasoning with diverse scene complexities, but evaluating such abilities is difficult due to the lack of benchmarks that are not only diverse and scalable but also fully customizable. Existing benchmarks offer limited customizability over the scene complexity and are incapable of isolating and analyzing specific VLM failure modes under distinct spatial conditions. To address this gap, instead of individually presenting benchmarks for different scene complexities, in this paper we present InfiniBench, a fully automated, customizable and user-friendly benchmark generator that can synthesize a theoretically infinite variety of 3D scenes with parameterized control on scene complexity. InfiniBench uniquely translates scene descriptions in natural language into photo-realistic videos with complex and physically plausible 3D layouts. This is achieved through three key innovations: 1) a LLM-based agentic framework that iteratively refines procedural scene constraints from scene descriptions; 2) a flexible cluster-based layout optimizer that generates dense and cluttered scenes previously intractable for procedural methods; and 3) a task-aware camera trajectory optimization method that renders scenes into videos with full object coverage as VLM input. Experiments demonstrate that InfiniBench outperforms state-of-the-art procedural and LLM-based 3D generation methods in prompt fidelity and physical plausibility, especially in high-complexity scenarios. We further showcased the usefulness of InfiniBench, by generating benchmarks for representative spatial reasoning tasks including measurement, perspective-taking and spatiotemporal tracking.