Gen-Searcher: Reinforcing Agentic Search for Image Generation

Dimensions overall score 9.0

• Gen-Searcher is the first trained search-augmented image generation agent that performs multi-hop reasoning and search to collect textual knowledge and reference images for grounded generation.method 95%
• Gen-Searcher improves Qwen-Image by around 16 points on the KnowGen benchmark.result 90%
• The system's quality heavily depends on the accuracy of retrieved web content, and incomplete or incorrect web data can lead to erroneous image outputs.limitation 85%
• Gen-Searcher uses agentic reinforcement learning with dual reward feedback (text-based and image-based) to provide stable and informative learning signals for GRPO training.method 80%
• The authors constructed two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images.technical 90%
• Standard text-to-image systems perform poorly on knowledge-intensive and search-grounded image generation, as shown by low K-Scores (around 9 to 15), while proprietary models perform substantially better.result 85%
• Gen-Searcher is equipped with three search tools, including a web text search tool, to perform multi-turn reasoning and information gathering.technical 80%
• The model was trained using 8 NVIDIA H800 GPUs, with Qwen3-VL-8B-Instruct as the base model, following a two-stage process of supervised fine-tuning and agentic RL training.method 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card