ImAgent统一框架让图像生成更准更稳，无需训练就能动态优化
ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation
- 用一个统一框架整合推理、生成和自评估，动态调整生成过程
- 在模糊提示下仍显著提升图像质量和语义一致性，超越基线模型
- 无需额外模型，适合对生成稳定性要求高的实际应用
近期文本到图像（T2I）模型在生成视觉逼真且语义一致的图像方面取得显著进展。然而，面对模糊或不完整的文本描述时，仍存在随机性和不一致性问题。现有方法如提示重写、best-of-N采样和自精炼虽可缓解问题，但通常需额外模块且独立运行，阻碍了测试时的可扩展性并增加计算开销。本文提出ImAgent，一种无需训练的统一多模态代理框架，将推理、生成与自评估集成于单一系统中，实现高效的测试时扩展。在策略控制器引导下，多个生成动作动态交互与自我组织，无需依赖外部模型即可提升图像保真度与语义对齐。在图像生成与编辑任务上的大量实验表明，ImAgent持续优于基线模型，甚至在基线失败时仍表现更优，凸显了统一多模态代理在测试时扩展下的自适应与高效生成潜力。
原文摘要 · Abstract (English)
Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when textual descriptions are vague or underspecified. Existing approaches, such as prompt rewriting, best-of-N sampling, and self-refinement, can mitigate these issues but usually require additional modules and operate independently, hindering test-time scaling efficiency and increasing computational overhead. In this paper, we introduce ImAgent, a training-free unified multimodal agent that integrates reasoning, generation, and self-evaluation within a single framework for efficient test-time scaling. Guided by a policy controller, multiple generation actions dynamically interact and self-organize to enhance image fidelity and semantic alignment without relying on external models. Extensive experiments on image generation and editing tasks demonstrate that ImAgent consistently improves over the backbone and even surpasses other strong baselines where the backbone model fails, highlighting the potential of unified multimodal agents for adaptive and efficient image generation under test-time scaling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。