Reproduce “Advances in Agentic Computer Graphics” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hengyu Liu, Jihyeon Je, Ruiqi Wang, Mingxuan Wu, Haven Feng, Qixing Huang, Georgios Pavlakos, Hao Zhang and 6 more
The authors present a graphics-focused taxonomy and system for comparing agentic graphics systems. The taxonomy covers tasks, models, harnesses, and graphics tools; the system records evidence and feedback. They analyze 350 papers published from 2024 through September 2026. Among 304 works using observation feedback, 77.0% use visual feedback, and 58.2% combine observation categories. These are corpus patterns, not validated annotations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.