AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning

Kaixun Jiang, Yuzheng Wang, Junjie Zhou, Pandeng Li, Zhihang Liu, Chen-Wei Xie, Zhaoyu Chen, Yun Zheng, Wenqiang Zhang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 21 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 cold-start SFT on tool-invocation and reflection data (ablation)GenAgent (Qwen2.5-VL-7B) · GenEval++overall score: 0.357 -> 0.507Improved
add cold-start SFT (ablation)GenAgent (Qwen2.5-VL-7B) · WISEoverall score: 0.63 -> 0.64No clear effect
add cold-start SFT (ablation)GenAgent (Qwen2.5-VL-7B) · Imagineoverall score: 6.258 -> 6.770Improved
add agentic RL after SFT (without pairwise reward) (ablation)GenAgent · GenEval++overall score: 0.507 -> 0.543Improved
add pairwise reflection reward r_pair to RL (ablation)GenAgent · GenEval++overall score: 0.543 -> 0.561Improved
add pairwise reflection reward r_pair to RL (ablation)GenAgent · WISEoverall score: 0.68 -> 0.69Improved
add pairwise reflection reward r_pair to RL (ablation)GenAgent · Imagineoverall score: 6.814 -> 6.825Improved
use tool invocation with FLUX.1-dev instead of single-pass rewrite only (ablation)GenAgent · GenEval++overall score: 0.482 -> 0.561Improved
swap the FLUX.1-dev tool for stronger Qwen-Image at inference without retrainingGenAgent · GenEval++overall score: 0.561 -> 0.725Improved
swap the FLUX.1-dev tool for stronger Qwen-Image at inference without retrainingGenAgent · Imagineoverall score: 6.825 -> 7.794Improved
wrap FLUX.1-dev with GenAgentFLUX.1-dev · WISEoverall score: 0.55 -> 0.69Improved
wrap FLUX.1-dev with GenAgentFLUX.1-dev · GenEval++overall score: 0.325 -> 0.561Improved

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