Gen-Searcher: Reinforcing Agentic Search for Image Generation
Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diver...
| Authors | Kaituo Feng, Manyuan Zhang, Shuang Chen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 30 March 2026 |
| Last updated at source | 22 May 2026 |
Connected in the knowledge graph
- GenSearcher/KnowGen-BenchDataset · cited by
- GenSearcher/Train-DataDataset · cited by
Models and datasets referencing this paper
- GenSearcher/KnowGen-BenchDataset
- GenSearcher/Train-DataDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.