The paper investigates the role of AI agents in analog layout generation, comparing direct layout drawing by large language models (LLMs) with using generator frameworks like gLayout. Experiments on SKY130 show that drawing layouts directly is costly in time and tokens, whereas building on a generator framework offers reusability and efficient verification across layout families. The authors propose that models should edit generator code and test changes on likely-failing family members, using the results to train local models that generalize edits at lower inference cost.
arXiv:2608.30751v1 Announce Type: new Abstract: Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whethe...
Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D...
arXiv:2510.14980v3 Announce Type: replace Abstract: Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate pro...
arXiv:2608.22390v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong potential in graphical user interface (GUI) generation, but reliable evaluation remains challengi...
arXiv:2607. 16409v1 Announce Type: cross Abstract: Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation.
arXiv:2606. 05268v1 Announce Type: cross Abstract: We present a pipeline for building and aggregating task-specific, LLM-generated weak (imperfect) verifiers into a strong verifier for spatial layout domains.
PlanCraft introduces a progressive approach to 3D residential scene generation that mirrors how architects design: starting with rough sketches and refining them over time. It leverages a large dataset of real floor plans to train a SketchPlan module that generates partial sketches at various completion levels, a PlanCraft‑Diff module that sharpens these sketches into precise vector floor plans, and a PlanCraft‑Agent that furnishes rooms within the established spatial contract. The method outperforms existing 2D and 3D baselines, achieving a 61.1% lower FID and a 15‑point lead in expert‑rated spatial rationality, even with only 25% sketch completion.
arXiv:2609.36064v1 Announce Type: cross Abstract: Foundation models are powerful generators, but many engineering domains require structured representations that general-purpose systems handle poorly...
arXiv:2606. 30429v1 Announce Type: new Abstract: Text-to-3D systems can now synthesize a mechanical part from a single sentence, yet the result is a shape to render, not a design to edit.
The paper audits frozen decoder‑only large language models (LLMs) on geometric reasoning tasks using parametric CAD constraints. It probes hidden states for linear decodability, forced‑choice generation, activation‑level influence, and behavioral steerability, finding that pretraining improves decoding of local geometric relations but not sketch‑level DOF status. The study shows that decodable information is not always actionable: generation often fails to express it, and steering interventions do not reliably control outputs, revealing divergences among decodability, generation, activation influence, and steerability.
VisCAD is a foundation model suite that tackles AI-assisted computer-aided design for industrial products, covering both part-level and assembly-level generation. Its core component, VisCAD‑M1, is a 27B model trained for part-level design generation and outperforms existing models on PubCADBench and RealCADBench, achieving a part-level score of 0.5540 and reaching 0.5797 when used as a test-time verifier. VisCAD also offers a domain-specific harness that improves complex assembly generation compared to general-purpose harnesses, showing quantitative and qualitative advantages.
The paper introduces domain-specific languages (DSLs) as an explicit representation layer to bridge the gap between high-level natural-language abstractions and concrete actions. Experiments on the visually-grounded “Hexagons” task and the “Text2CAD” benchmark show that code generation using a human-curated DSL yields dramatic performance gains, especially at higher abstraction levels, while automatically induced DSLs only partially recover these gains. The study highlights that the right representation can close much of the performance gap caused by abstraction, but that automatically learning such representations remains a challenge.