AI Paper Atlas

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

PaperBanana: Automating Academic Illustration for AI Scientists

Dawei Zhu, Rui Meng, Yale Song, Xiyu Wei, Sujian Li, Tomas Pfister, Jinsung Yoon

ICML 2026 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 1 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
use PaperBanana agentic workflow instead of vanilla image generationNano-Banana-Pro · PaperBananaBench (diagrams)Overall win score: 43.2 -> 60.2Improved
add Critic refinement (3 iterations) (ablation)PaperBanana · PaperBananaBench (diagrams)Overall win score: 45.6 -> 60.2Improved
add Critic refinement (3 iterations) (ablation)PaperBanana · PaperBananaBench (diagrams)Faithfulness: 30.7 -> 45.8Improved
increase Critic iterations from 1 to 3 (ablation)PaperBanana · PaperBananaBench (diagrams)Overall win score: 51.8 -> 60.2Improved
add Stylist agent (ablation)PaperBanana (no Critic) · PaperBananaBench (diagrams)Conciseness: 61.7 -> 79.2Improved
add Stylist agent (ablation)PaperBanana (no Critic) · PaperBananaBench (diagrams)Faithfulness: 39.2 -> 30.7Hurt
use semantic retriever instead of random retriever (ablation)PaperBanana (no Stylist, no Critic) · PaperBananaBench (diagrams)Overall win score: 48.3 -> 49.2No clear effect
add reference examples (retriever) to planner (ablation)PaperBanana (no Stylist, no Critic) · PaperBananaBench (diagrams)Overall win score: 44.2 -> 49.2Improved
add 10 few-shot examples to promptNano-Banana-Pro · PaperBananaBench (diagrams)Overall win score: 43.2 -> 41.8No clear effect
swap Nano-Banana-Pro for GPT-Image-1.5 as image generatorPaperBanana · PaperBananaBench (diagrams)Overall win score: 60.2 -> 19.0Hurt
use image generation instead of code for VisualizerPaperBanana · Statistical plotsFaithfulness and ConcisenessMixed
apply PaperBanana instead of vanilla Gemini-3-ProGemini-3-Pro · Statistical plots (ChartMimic-derived, 240 cases)Overall: +4.1%Improved

Later papers that compared with this method

1 later accepted paper reports PaperBanana as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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