AI Paper Atlas

Research map / Large language models / Agents, code and math

Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration

ZHUOLING Li, Jiarui Zhang, Ping Hu, Jason Kuen, Jiuxiang Gu, Hossein Rahmani, Jun Liu

ECCV 2026 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 4 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 drawing middleware repository (ablation)FigAgent · FigAgentBenchVLM score: 39.5 -> 61.4Improved
add drawing middleware repository (ablation)FigAgent · FigAgentBenchNA F1: 26.5 -> 51.4Improved
add Explore-and-Select strategy (ablation)FigAgent · FigAgentBenchVLM score: 48.2 -> 61.4Improved
add Explore-and-Select instead of greedy selection (ablation)FigAgent · FigAgentBenchVLM score: 54.3 -> 61.4Improved
add Explore-and-Select instead of greedy selection (ablation)FigAgent · FigAgentBenchNA F1: 41.9 -> 51.4Improved
add middleware evolution (ablation)FigAgent · FigAgentBenchVLM score: 45.5 -> 61.4Improved
add selection operation in evolution (ablation)FigAgent · FigAgentBenchVLM score: 47.6 -> 61.4Improved
add mutation operation in evolution (ablation)FigAgent · FigAgentBenchVLM score: 59.3 -> 61.4Improved
add crossover operation in evolution (ablation)FigAgent · FigAgentBenchVLM score: 54.2 -> 61.4Improved
add new middlewares directly without evolution (ablation)FigAgent (2023 repository) · FigAgentBenchVLM score: 49.5 -> 56.8Improved
add new middlewares via evolution (ablation)FigAgent (2023 repository) · FigAgentBenchVLM score: 49.5 -> 64.9Improved
integrate new middlewares through evolution instead of direct adding (ablation)FigAgent (2023 repository) · FigAgentBenchNA F1: 37.4 -> 50.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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