arXiv AI
PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 2
LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction
LiteReality-Agent is an agentic system that reconstructs real indoor environments into realistic, articulated, and simulation-ready 3D scenes from RGB‑D scans. It treats reconstruction as a coding problem, where a coding agent iteratively edits a Python script (Room.py) using specialized tools, while an observe‑edit‑verify harness ensures evidence gathering, measurement, verification, layout optimisation, simulation readiness, and quality control. The system outperforms recent models like Astra and Fable in geometric accuracy, visual realism, and simulation compatibility, and its modular framework is positioned as a robust foundation for future agent‑driven reconstruction tasks.
arXiv AI
Oct 5
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
arXiv:2610.03715v1 Announce Type: cross Abstract: We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as execu...
arXiv Computer Vision
Sep 30
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
arXiv:2609.36380v1 Announce Type: new Abstract: A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program...
arXiv Computer Vision
Oct 8
Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
arXiv:2610.04432v2 Announce Type: replace Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on...
arXiv AI
Jul 3
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
arXiv:2607. 01766v1 Announce Type: new Abstract: LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output.
arXiv AI
Aug 21
ChronoAgentic: A Code-based Multi-Agent World Simulator for Physically Grounded Simulation Construction
arXiv:2605. 14398v3 Announce Type: replace Abstract: Video-based world models generate visually plausible rollouts, but since they infer dynamics in latent states, they enforce no explicit physical constraints: contacts drift, shapes distort, and motion loses consistency.