Diffbrief Engineering daily

← Wednesday, September 30, 2026AgentsPaper

LEGO-Anything uses a coding agent to build editable 3D scenes

huggingface.co by Xirui Li et al. Editor score 8/10

A coding agent writes and revises Blender programs, while LEGO-Bench measures artifact validity, geometry, and appearance across 208 images; the strongest reported scores are 53.4% indoors and 39.6% outdoors. The benchmark’s separate metrics expose where iterative coding agents still fail at visual reconstruction.

What
LEGO-Anything reconstructs 3D scenes from images as editable scene programs, using a coding agent that iteratively writes and executes Blender code.
Method
The agent inspects scenes and renderings, then revises the program; LEGO-Bench evaluates artifact validity, visible-surface geometry, and rendered appearance.
Why it matters
Editable outputs support inspection and revision, while evaluations expose weak initialization, regressive edits, and unreliable self-evaluation in scene-building agents.
writes executes render inspection coding agent Blender code scenes renderings
A coding agent iterates on Blender code using the resulting scenes and renderings. Sketched from the article's own text.

Read on huggingface.co →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.

Your note

Private to you. Stored in this browser, and synced to your account when you are signed in.