# Advances in Agentic Computer Graphics

**Authors:** Hengyu Liu, Jihyeon Je, Ruiqi Wang, Mingxuan Wu, Haven Feng, Qixing Huang, Georgios Pavlakos, Hao Zhang, Jiajun Wu, Maneesh Agrawala, Leonidas Guibas, R. Kenny Jones, Shangzhe Wu, Guandao Yang  
**Lab:** The University of Texas at Austin · **Published:** 31 Oct 2026 · **Upvotes:** 111 · **Level:** Intermediate  
**Links:** [arXiv](https://arxiv.org/abs/2611.01860) · [PDF](https://arxiv.org/pdf/2611.01860) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.01860.html)

## Curator's notes

**TL;DR:** The paper proposes a taxonomy and a literature analysis system for agentic computer graphics research.

- **What's new:** It introduces a unified taxonomy for agentic graphics systems and an automated literature analysis tool, unlike prior ad‑hoc surveys.
- **Why it matters:** It helps developers quickly understand and leverage agent‑driven graphics tools across many tasks.

## Abstract

Computer graphics is built on code. Large language model (LLM) agents can now generate graphics code and iteratively refine it through various feedback. This capability opens the door to a potentially new paradigm of computer graphics, with graphics algorithms increasingly built around agentic systems to automate progressively complex tasks. Over the past years, research on agentic graphics has expanded rapidly across a diverse range of tasks. This rapid growth makes it increasingly difficult for manual literature reviews to keep pace with new developments. At the same time, similar ideas are often described using different terminology across these tasks, further complicating efforts to develop a systematic understanding of the field. In this report, we address these challenges through two contributions. First, we introduce a unified taxonomy for characterizing agentic systems across diverse computer graphics tasks. Second, we develop an agentic literature system that can assist human researchers in analyzing existing and newly published papers at scale. Building on these contributions, we analyze emerging research trends and discuss open challenges in coordinating agents and tools across graphics tasks, designing interfaces and representations for human-agent collaboration, sustaining long-horizon planning and refinement, and reliably evaluating interactive graphics systems.

## What you could build

1. Create a tool that uses the taxonomy to recommend suitable agentic graphics pipelines for user projects
2. Develop a plugin that queries the literature system to suggest recent agentic methods for a given graphics problem
3. Build an interface that lets artists iteratively refine code with LLM agents using the identified coordination patterns

## Quiz yourself

What two main contributions does the paper claim to make?

**Answer:** It introduces a unified taxonomy for characterizing agentic graphics systems and develops an agentic literature system for large‑scale paper analysis.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.