# LEGO-Anything: Coding Agents for 3D Scene Reconstruction

arXiv: https://arxiv.org/abs/2609.36380 · HTML: https://mlsanity.com/paper/2609.36380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 37)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model](https://mlsanity.com/paper/2410.13882/) (2024)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [Panoptic 3D Scene Reconstruction From a Single RGB Image](https://mlsanity.com/paper/2111.02444/) (2021)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View](https://mlsanity.com/paper/2404.03421/) (2024)
- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image](https://mlsanity.com/paper/2511.13648/) (2025)
- [The Scene Language: Representing Scenes with Programs, Words, and Embeddings](https://mlsanity.com/paper/2410.16770/) (2024)
- [Articraft: An Agentic System for Scalable Articulated 3D Asset Generation](https://mlsanity.com/paper/2605.15187/) (2026)
- [LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans](https://mlsanity.com/paper/2507.02861/) (2025)
- [SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning](https://mlsanity.com/paper/2605.09423/) (2026)
- [3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code](https://mlsanity.com/paper/2606.01057/) (2026)
- [SceneGenAgent: Precise Industrial Scene Generation with Coding Agent](https://mlsanity.com/paper/2410.21909/) (2024)
- [3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework](https://mlsanity.com/paper/2512.17459/) (2025)
- [Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models](https://mlsanity.com/paper/2606.02580/) (2026)
- [WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis](https://mlsanity.com/paper/2606.01869/) (2026)
- [P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning](https://mlsanity.com/paper/2606.11152/) (2026)
- [ClawEnvKit: Automatic Environment Generation for Claw-Like Agents](https://mlsanity.com/paper/2604.18543/) (2026)
- [Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations](https://mlsanity.com/paper/2604.27106/) (2026)
- [REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image](https://mlsanity.com/paper/2605.30338/) (2026)
- [Agentic Hardware Design as Repository-Level Code Evolution](https://mlsanity.com/paper/2606.28279/) (2026)
- [SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM](https://mlsanity.com/paper/2603.23386/) (2026)
- [Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models](https://mlsanity.com/paper/2601.01321/) (2026)

## Abstract (arXiv)

A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program whose execution yields a scene that can be inspected, edited, and queried. We present LEGO-Anything, an Image-to-Code framework in which a coding agent iteratively writes and executes Blender code, inspects scenes and renderings, and revises the program. To evaluate end-to-end scene recovery, we introduce LEGO-Bench, a simulator-grounded benchmark with 208 images from 104 diverse indoor and outdoor scenes. LEGO-Bench separately scores artifact validity, visible-surface geometry, and rendered appearance. Its simulator-grounded design enables extensibility and precise automatic evaluation. Among evaluated agents, GPT-6-astra achieves the strongest overall results, with 53.4% indoor and 39.6% outdoor scores, yet substantial gaps remain between delivering valid scene artifacts and faithfully recovering scene geometry and appearance. Analysis of agent construction trajectories reveals three recurring issues: weak scene initialization, regressive edits during iteration, and unreliable self-evaluation. These findings motivate LEGO-Plugin, a training-free harness plugin for more controlled iterative scene construction, which improves all six evaluated models, with relative gains of up to 62.7% in overall score. Finally, we test whether reconstructed scenes can represent natural images and support vision tasks. In LEGO-World, we derive object detections, instance masks, and relative depth as deterministic queries on scenes reconstructed by GPT-6-astra. These readouts show non-trivial performance across all three tasks but fall well short of specialized vision models, suggesting that program-constructed scenes from current coding agents are a promising but not yet sufficiently precise representation of natural images.