# Preference-Guided Prompt Optimization for Text-to-Image Generation

arXiv: https://arxiv.org/abs/2602.13131 · HTML: https://mlsanity.com/paper/2602.13131/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2026.

## Built on by (most cited first, 2 of 2)

- [From Words to Widgets for Controllable LLM Generation](https://mlsanity.com/paper/2604.10925/) (2026)
- [Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image Diffusion](https://mlsanity.com/paper/2603.14936/) (2026)

## Abstract (arXiv)

Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt refinement tools heavily rely on human effort, while prompt optimization methods focus on numerical functions and are not designed for human-centered generative tasks, where feedback is better expressed as binary preferences and demands convergence within few iterations. We present APPO, a preference-guided prompt optimization algorithm. Instead of iterating prompts, users only provide binary preferential feedback. APPO adaptively balances its strategies between exploiting user feedback and exploring new directions, yielding effective and efficient optimization. We evaluate APPO on image generation, and the results show APPO enables achieving satisfactory outcomes in fewer iterations with lower cognitive load than manual prompt editing. We anticipate APPO will advance human-AI collaboration in generative tasks by leveraging user preferences to guide complex content creation.