This repository contains the Supervised Fine-Tuning (SFT) model presented in the paper: Gen-Searcher: Reinforcing Agentic Search for Image Generation.

This is an intermediate model prepared for subsequent reinforcement learning (RL) training using the GRPO algorithm with dual reward feedback.

🌐 Project Page | 💻 Code | 📖 Paper

We introduce Gen-Searcher, as the first attempt to train a multimodal deep research agent for image generation that requires complex real-world knowledge. Gen-Searcher can search the web, browse evidence, reason over multiple sources, and search visual references before generation, enabling more accurate and up-to-date image synthesis in real-world scenarios.

We build two dedicated training datasets Gen-Searcher-SFT-10k, Gen-Searcher-RL-6k and one new benchmark KnowGen for search-grounded image generation.

Gen-Searcher achieves significant improvements, delivering 15+ point gains on the KnowGen and WISE benchmarks. It also demonstrates strong transferability to various image generators.

All code, models, data, and benchmark are fully released.

For more examples, please refer to our website [🌐 Project Page].

If you find our work helpful for your research, please consider citing our work: