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

We introduce GenAgent, an agentic framework that unifiesvisual understanding and generation. GenAgent overcomes the limita-tions of tightly coupled unified models (which suffer from understand-ing–generation trade-offs and high training data costs) and the struc-tural bottlenecks of existing complex multi-model pipelines through aflexible, decoupled architecture: Understanding is handled by a singlemultimodal model, while generation is achieved by treating image gen-eration models as invokable tools. Given an image prompt, GenAgentadaptively engages in reasoning, tool invocation, visual judgment, andreflection to iteratively refine outputs until the criteria are met. We em-ploy a two-stage training strategy: first, we cold-start the agent with su-pervised fine-tuning on high-quality tool-invocation and reflection datato bootstrap multi-turn agent behaviors; second, we perform end-to-endagentic reinforcement learning, combining pointwise rewards (final im-age quality) and pairwise rewards (reflection accuracy), and utilizinga round-aware trajectory resampling strategy to balance improvementsacross distinct capabilities. Without modifying the underlying genera-tors, GenAgent significantly boosts the base model (FLUX.1-dev) by23.6% on GenEval++ and 14.0% on WISE. Beyond substantial per-formance gains, our framework demonstrates three key emergent prop-erties: (1) cross-tool generalization to generators with varying capabili-ties, (2) test-time scaling with consistent improvements across interactionrounds, and (3) task-adaptive reasoning. Project page: https://deep-kaixun.github.io/genagent-page/