Lune

EMNLP Findings2025

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation

Wen Ye, Zhaocheng Liu, Yuwei Gui, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang

Abstract

Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as finetuning, are model-specific and require training, while prior automatic prompt optimization (APO) approaches typically lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness. Meanwhile, test-time scaling methods operate on fixed prompts and on noise or sample numbers, limiting their interpretability and adaptability. To solve these, we introduce a flexible and efficient test-time prompt optimization strategy that operates directly on the input text. We propose a plug-and-play multiagent system called GenPilot, integrating error analysis, clustering-based adaptive exploration, fine-grained verification, and a memory module for iterative optimization. Our approach is model-agnostic, interpretable, and well-suited for handling long and complex prompts. Simultaneously, we summarize the common patterns of errors and the refinement strategy, offering more experience and encouraging further exploration. Experiments on DPG-bench and Geneval with improvements of up to 16.9% and 5.7% demonstrate the strong capability of our methods in enhancing the text and image consistency and structural coherence of generated images, revealing the effectiveness of our test-time prompt optimization strategy. The code is available at https://github.com/27yw/GenPilot.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Learning Transferable Visual Models From Natural Language Supervision
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on16

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  3. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  4. Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
  5. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations

Related papers

  1. coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image GenerationChunhan Li, Qifeng Wu, Jia-Hui Pan, Ka-Hei Hui, Jingyu Hu, Yuming Jiang, Bin Sheng, Xihui Liu, Wenjuan Gong, Zhengzhe LiuCVPR Findings 2026
  2. T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive GenerationChieh-Yun Chen, Min Shi, Gong Zhang, Humphrey ShiICCV 2025 · 1 citation
  3. UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and GenerationRui Tian, Mingfei Gao, Mingze Xu, Jiaming Hu et al.NeurIPS 2025 · 35 citations
  4. RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image AlignmentLiyao Jiang, Ruichen Chen, Chao Gao, Di NiuCVPR 2026 · 7 citations
  5. Proactive Agents for Multi-Turn Text-to-Image Generation Under UncertaintyMeera Hahn, Wenjun Zeng, Nithish Kannen, Rich Galt et al.ICML 2025
Dusk over the sea between two cliffs drawn in fine vertical lines