# CRAFT: Continuous Reasoning and Agentic Feedback Tuning for Multimodal Text-to-Image Generation

arXiv: https://arxiv.org/abs/2512.20362 · HTML: https://mlsanity.com/paper/2512.20362/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## 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, 13 of 13)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration](https://mlsanity.com/paper/2509.10704/) (2025)

## Built on by (most cited first, 6 of 6)

- [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)
- [Mind the Gap: Diagnosing Constraint Discovery Failures in Text-in-Image Editing](https://mlsanity.com/paper/2606.15982/) (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)
- [Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation](https://mlsanity.com/paper/2610.16224/) (2026)

## Abstract (arXiv)

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making their behavior difficult to interpret, control, or stop reliably. In contrast, large language models have benefited from explicit, structured forms of **thinking** based on verification, targeted correction, and early stopping. We introduce CRAFT (Continuous Reasoning and Agentic Feedback Tuning), a training-free and model-agnostic framework for multimodal image generation. CRAFT transforms a user prompt into a set of explicit, dependency-structured visual constraints, verifies generated images using a vision-language model, and performs targeted prompt updates only when specific constraints are violated. This iterative process includes an explicit stopping criterion, resulting in an interpretable and controllable inference-time refinement loop. Across multiple model families and challenging benchmarks, CRAFT consistently improves compositional accuracy, text rendering, and preference-based evaluations, with particularly strong gains for lightweight generators. Importantly, these improvements incur only a negligible inference-time overhead, allowing smaller or cheaper models to approach the quality of substantially more expensive systems. Our results suggest that explicitly structured, constraint-driven inference-time reasoning is a key ingredient for improving the reliability of multimodal generative models.