AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement

Zhengfei Kuang, Rui Lin, Long Zhao, Gordon Wetzstein, Saining Xie, Sanghyun Woo

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add constraint solver and visual API tool library (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)plausibility: 3.484 -> 3.796Improved
add constraint solver and visual API tool library (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)collision rate: 0.495 -> 0.000Improved
add adaptive backtracking (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)collision rate: 0.036 -> 0.000Improved
add adaptive backtracking (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)floating rate: 0.054 -> 0.000Improved
add MCP-based tools instead of raw Blender scripts (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)collision rate: 0.603 -> 0.000Improved
add planner target coordinates (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)consistency: 3.526 -> 3.592Improved
add planner target coordinates (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)collision rate: 0.000 -> 0.000No clear effect
use multi-agent planner/executor/evaluator instead of single agent (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)consistency: 3.328 -> 3.592Improved
use multi-agent instead of single agent (ablation)VULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)collision rate: 0.000 -> 0.000No clear effect
VULCAN full system vs best single-step baseline FirePlaceVULCAN · VULCAN benchmark (25 scenes, 111 unit tasks)consistency: 3.135 -> 3.592Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy