aDSL: Agentic 3D Creation via Joint Agent-Program Design
- Published
- Source
- arXiv
- Paper number
- 946
- Field
- Computer Vision
- arXiv ID
- 2608.17975
Key points
- The work starts from the observation that LLMs often miss precise numerical placements, such as a leg's exact coordinates, but reason well about structure, such as placing four chair legs beneath the corners of a seat.
- aDSL emphasizes compositionality and spatial-relation operators, so agents do not have to manipulate low-level numerical values directly.
- Disabling the self-correction loop reduced the visual question-answering score to 61.53 and also lowered the execution success rate, showing that iterative verification is essential.
- Removing the planning stage increased the average number of revision rounds from 4.25 to 5.58, showing that structural decomposition determines efficiency.
- An interactive front end, including an OpenClaw demonstration, supports iterative editing, while integration with an external high-fidelity generator preserves structure and improves detail.
Paper links
External research summaries. These are not HDATF publications or measured product results.