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

arXiv: https://arxiv.org/abs/2601.18543 · HTML: https://mlsanity.com/paper/2601.18543/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 29 of 29)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2503.07265/) (2025)
- [Thyme: Think Beyond Images](https://mlsanity.com/paper/2508.11630/) (2025)
- [DeepEyesV2: Toward Agentic Multimodal Model](https://mlsanity.com/paper/2511.05271/) (2025)
- [X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again](https://mlsanity.com/paper/2507.22058/) (2025)
- [Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation](https://mlsanity.com/paper/2508.09987/) (2025)
- [rStar2-Agent: Agentic Reasoning Technical Report](https://mlsanity.com/paper/2508.20722/) (2025)
- [BLIP3o-NEXT: Next Frontier of Native Image Generation](https://mlsanity.com/paper/2510.15857/) (2025)
- [GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning](https://mlsanity.com/paper/2505.17022/) (2025)
- [PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting](https://mlsanity.com/paper/2509.04545/) (2025)
- [Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm](https://mlsanity.com/paper/2511.04570/) (2025)
- [Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO](https://mlsanity.com/paper/2505.17017/) (2025)
- [RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning](https://mlsanity.com/paper/2505.17540/) (2025)
- [Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation](https://mlsanity.com/paper/2509.18639/) (2025)
- [SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards](https://mlsanity.com/paper/2506.07963/) (2025)

## Built on by (most cited first, 24 of 24)

- [Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation](https://mlsanity.com/paper/2602.01756/) (2026)
- [GEMS: Agent-Native Multimodal Generation with Memory and Skills](https://mlsanity.com/paper/2603.28088/) (2026)
- [GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation](https://mlsanity.com/paper/2605.21605/) (2026)
- [Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation](https://mlsanity.com/paper/2606.26907/) (2026)
- [NEWTON: Agentic Planning for Physically Grounded Video Generation](https://mlsanity.com/paper/2605.18396/) (2026)
- [GenClaw: Code-Driven Agentic Image Generation](https://mlsanity.com/paper/2605.30248/) (2026)
- [Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation](https://mlsanity.com/paper/2607.05382/) (2026)
- [COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows](https://mlsanity.com/paper/2607.01709/) (2026)
- [GenRouter: Unified Workflow Routing for Agentic Image Generation](https://mlsanity.com/paper/2608.16721/) (2026)
- [AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation](https://mlsanity.com/paper/2603.28068/) (2026)
- [ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation](https://mlsanity.com/paper/2608.04436/) (2026)
- [MemoGen: Can Past Experience Improve Future Text-to-Image Generation?](https://mlsanity.com/paper/2606.03243/) (2026)
- [GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing](https://mlsanity.com/paper/2604.05076/) (2026)
- [WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing](https://mlsanity.com/paper/2609.05171/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [AgenticGen: Reward-Guided Agentic Video Generation for Advertising](https://mlsanity.com/paper/2609.09187/) (2026)
- [AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization](https://mlsanity.com/paper/2609.29517/) (2026)
- [SegBanana: Steering Unified Multimodal Models into Medical Segmenters](https://mlsanity.com/paper/2609.34235/) (2026)
- [SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering](https://mlsanity.com/paper/2609.34335/) (2026)
- [AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation](https://mlsanity.com/paper/2609.35530/) (2026)
- [Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation](https://mlsanity.com/paper/2610.07250/) (2026)
- [MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing](https://mlsanity.com/paper/2610.12963/) (2026)
- [Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation](https://mlsanity.com/paper/2610.16224/) (2026)
- [APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation](https://mlsanity.com/paper/2610.18097/) (2026)

## Abstract (arXiv)

We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model. Unlike unified models that face expensive training costs and understanding-generation trade-offs, GenAgent decouples these capabilities through an agentic framework: understanding is handled by the multimodal model itself, while generation is achieved by treating image generation models as invokable tools. Crucially, unlike existing modular systems constrained by static pipelines, this design enables autonomous multi-turn interactions where the agent generates multimodal chains-of-thought encompassing reasoning, tool invocation, judgment, and reflection to iteratively refine outputs. We employ a two-stage training strategy: first, cold-start with supervised fine-tuning on high-quality tool invocation and reflection data to bootstrap agent behaviors; second, end-to-end agentic reinforcement learning combining pointwise rewards (final image quality) and pairwise rewards (reflection accuracy), with trajectory resampling for enhanced multi-turn exploration. GenAgent significantly boosts base generator(FLUX.1-dev) performance on GenEval++ (+23.6%) and WISE (+14%). Beyond performance gains, our framework demonstrates three key properties: 1) cross-tool generalization to generators with varying capabilities, 2) test-time scaling with consistent improvements across interaction rounds, and 3) task-adaptive reasoning that automatically adjusts to different tasks. Our code will be available at hrefhttps://github.com/deep-kaixun/GenAgentthis url.