# VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model

arXiv: https://arxiv.org/abs/2603.08812 · HTML: https://mlsanity.com/paper/2603.08812/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens](https://mlsanity.com/paper/2410.13863/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Captain Cinema: Towards Short Movie Generation](https://mlsanity.com/paper/2507.18634/) (2025)
- [JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization](https://mlsanity.com/paper/2511.23002/) (2025)
- [ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems](https://mlsanity.com/paper/2409.01392/) (2024)
- [MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio](https://mlsanity.com/paper/2503.05242/) (2025)
- [Next Patch Prediction for Autoregressive Visual Generation](https://mlsanity.com/paper/2412.15321/) (2024)
- [ReasonEdit: Towards Reasoning-Enhanced Image Editing Models](https://mlsanity.com/paper/2511.22625/) (2025)
- [ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback](https://mlsanity.com/paper/2505.17908/) (2025)
- [ComfyUI-R1: Exploring Reasoning Models for Workflow Generation](https://mlsanity.com/paper/2506.09790/) (2025)
- [ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation](https://mlsanity.com/paper/2503.17671/) (2025)
- [VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation](https://mlsanity.com/paper/2603.02681/) (2026)

## Built on by (most cited first, 1 of 1)

- [DramaDirector: Geometry-Guided Short Drama Generation](https://mlsanity.com/paper/2606.24107/) (2026)

## Abstract (arXiv)

Visual content generation has advanced from single-image to multi-image workflows, yet existing agents remain largely plan-driven and lack systematic reflection mechanisms to correct mid-trajectory visual errors. To address this limitation, we propose VisionCreator-R1, a native visual generation agent with explicit reflection, together with a Reflection-Plan Co-Optimization (RPCO) training methodology. Through extensive experiments and trajectory-level analysis, we uncover reflection-plan optimization asymmetry in reinforcement learning (RL): planning can be reliably optimized via plan rewards, while reflection learning is hindered by noisy credit assignment. Guided by this insight, our RPCO first trains on the self-constructed VCR-SFT dataset with reflection-strong single-image trajectories and planning-strong multi-image trajectories, then co-optimization on VCR-RL dataset via RL. This yields our unified VisionCreator-R1 agent, which consistently outperforms Gemini2.5Pro on existing benchmarks and our VCR-bench covering single-image and multi-image tasks.