Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models

ArXi:2605.09218v1 Announce Type: cross 3D scene understanding spans reasoning about free space, object grounding, hypothetical object insertions, complex geometric relationships, and integrating all of these with external tools and data sources. Existing 3D understanding methods typically rely on large-scale 3D-language