# Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration

arXiv: https://arxiv.org/abs/2509.10704 · HTML: https://mlsanity.com/paper/2509.10704/

## Key facts

- Cited by 19 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 39 of its 47 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)
- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 30 of 39)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2503.07265/) (2025)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [What You See is What You Read? Improving Text-Image Alignment Evaluation](https://mlsanity.com/paper/2305.10400/) (2023)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [Self-Evaluation Improves Selective Generation in Large Language Models](https://mlsanity.com/paper/2312.09300/) (2023)

## Built on by (most cited first, 19 of 19)

- [VISTA: A Test-Time Self-Improving Video Generation Agent](https://mlsanity.com/paper/2510.15831/) (2025)
- [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)
- [coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation](https://mlsanity.com/paper/2603.12829/) (2026)
- [CRAFT: Continuous Reasoning and Agentic Feedback Tuning for Multimodal Text-to-Image Generation](https://mlsanity.com/paper/2512.20362/) (2025)
- [A2RD: Agentic Autoregressive Diffusion for Long Video Consistency](https://mlsanity.com/paper/2605.06924/) (2026)
- [Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment](https://mlsanity.com/paper/2512.07702/) (2025)
- [GenRouter: Unified Workflow Routing for Agentic Image Generation](https://mlsanity.com/paper/2608.16721/) (2026)
- [Generation Navigator: A State-Aware Agentic Framework for Image Generation](https://mlsanity.com/paper/2605.17969/) (2026)
- [MemoGen: Can Past Experience Improve Future Text-to-Image Generation?](https://mlsanity.com/paper/2606.03243/) (2026)
- [LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models](https://mlsanity.com/paper/2512.13290/) (2025)
- [Visual Persuasion: What Influences Decisions of Vision-Language Models?](https://mlsanity.com/paper/2602.15278/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short](https://mlsanity.com/paper/2606.09380/) (2026)
- [APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection](https://mlsanity.com/paper/2606.11459/) (2026)
- [Semantic Browsing: Controllable Diversity for Image Generation](https://mlsanity.com/paper/2606.23679/) (2026)
- [Reasoning with Image Generation](https://mlsanity.com/paper/2609.16409/) (2026)
- [AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation](https://mlsanity.com/paper/2609.35530/) (2026)
- [Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation](https://mlsanity.com/paper/2610.16224/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manual, iterative prompt engineering over often underspecified prompts. This paper introduces Maestro, a novel self-evolving image generation system that enables T2I models to autonomously self-improve generated images through iterative evolution of prompts, using only an initial prompt. Maestro incorporates two key innovations: 1) self-critique, where specialized multimodal LLM (MLLM) agents act as 'critics' to identify weaknesses in generated images, correct for under-specification, and provide interpretable edit signals, which are then integrated by a 'verifier' agent while preserving user intent; and 2) self-evolution, utilizing MLLM-as-a-judge for head-to-head comparisons between iteratively generated images, eschewing problematic images, and evolving creative prompt candidates that align with user intents. Extensive experiments on complex T2I tasks using black-box models demonstrate that Maestro significantly improves image quality over initial prompts and state-of-the-art automated methods, with effectiveness scaling with more advanced MLLM components. This work presents a robust, interpretable, and effective pathway towards self-improving T2I generation.