REVIEW 12 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
LL3M: Large Language 3D Modelers
read the original abstract
We present LL3M, a multi-agent system that leverages pretrained large language models (LLMs) to generate 3D assets by writing interpretable Python code in Blender. We break away from the typical generative approach that learns from a collection of 3D data. Instead, we reformulate shape generation as a code-writing task, enabling greater modularity, editability, and integration with artist workflows. Given a text prompt, LL3M coordinates a team of specialized LLM agents to plan, retrieve, write, debug, and refine Blender scripts that generate and edit geometry and appearance. The generated code works as a high-level, interpretable, human-readable, well-documented representation of scenes and objects, making full use of sophisticated Blender constructs (e.g. B-meshes, geometry modifiers, shader nodes) for diverse, unconstrained shapes, materials, and scenes. This code presents many avenues for further agent and human editing and experimentation via code tweaks or procedural parameters. This medium naturally enables a co-creative loop in our system: agents can automatically self-critique using code and visuals, while iterative user instructions provide an intuitive way to refine assets. A shared code context across agents enables awareness of previous attempts, and a retrieval-augmented generation knowledge base built from Blender API documentation, BlenderRAG, equips agents with examples, types, and functions empowering advanced modeling operations and code correctness. We demonstrate the effectiveness of LL3M across diverse shape categories, style and material edits, and user-driven refinements. Our experiments showcase the power of code as a generative and interpretable medium for 3D asset creation. Our project page is at https://threedle.github.io/ll3m.
Forward citations
Cited by 12 Pith papers
-
P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning
P3D-Bench is a benchmark with three task families that scores MLLMs on generating executable parametric 3D programs, finding failures in precise geometry and part assembly.
-
3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis
3D-CoS represents 3D objects as Blender code generated by VLMs, with workflows for planning, RAG, and agents, showing better edit fidelity than point-cloud baselines.
-
Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models
SEIG uses staged VLM prompting to output executable Blender programs that reconstruct editable 3D scenes from single images, showing improved fidelity over non-staged baselines.
-
Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
-
Training-Free Dense Hand Contact Estimation with Multi-Modal Large Language Models
ContactPrompt uses part-wise vertex grids and multi-stage part-conditioned reasoning in MLLMs to achieve training-free dense hand contact estimation that outperforms prior supervised methods.
-
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to...
-
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperf...
-
HandMade: Spatial Prompting for Generative 3D Creation with Part-Labeled VR Sketches
HandMade converts segmented VR strokes into multi-view part guidance and structured prompts so generative 3D models better preserve user-specified spatial scaffolds than text-only or sketch baselines.
-
Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
Prox-E is a training-free pipeline that abstracts 3D shapes into editable geometric primitives, uses a VLM to specify changes, and guides a generative model to apply precise local edits.
-
CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation
CMAG combines 3D concept scaffolding, prompt decomposition, taxonomy routing, hybrid retrieval, and agentic VLM verification to assemble topologically consistent avatars from catalog assets given free-form text prompts.
-
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Code-as-Room is an MLLM-based agentic pipeline that parses top-down images into multi-stage Blender code synthesis with cross-stage memory to generate functional 3D rooms.
-
ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python
ProcFunc introduces a Python library with function-oriented abstractions for procedural 3D generation in Blender, enabling combinatorial scene creation and demonstrated via a new indoor room generator with composition...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.