{"ID":2858896,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07217","arxiv_id":"2510.07217","title":"GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation","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 fine-tuning, 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 multi-agent 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.","short_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 fine-tuning, are model-specific and require training, while prior automatic prompt optimization...","url_abs":"https://arxiv.org/abs/2510.07217","url_pdf":"https://arxiv.org/pdf/2510.07217v1","authors":"[\"Wen Ye\",\"Zhaocheng Liu\",\"Yuwei Gui\",\"Tingyu Yuan\",\"Yunyue Su\",\"Bowen Fang\",\"Chaoyang Zhao\",\"Qiang Liu\",\"Liang Wang\"]","published":"2025-10-08T16:51:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":608595,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2858896,"paper_url":"https://arxiv.org/abs/2510.07217","paper_title":"GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation","repo_url":"https://github.com/27yw/GenPilot","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}