AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation

  • 类型：arxiv
  • 标识：2609.35530
  • 链接：https://arxiv.org/abs/2609.35530
  • 主分类：multimodal
  • 形态：method
  • TLDR：Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation remains challenging: models may omit or duplicate subjects from the references, or produce images in which multiple subjects appear unnaturally pasted. Recent work has proposed image generation agents that combine image generation models, reasoning models, and a harness, which is an executable program that specifies how reference images are interpreted, how generation is performed, how outputs are diagnosed, and how the final image is selected.
  • 副分类：agent
  • 待LLM分类：否
  • 标题中文：AutoRef：面向 Agentic 多参考图生成的 Harness 优化
  • TLDR中文：近期图像生成模型可接受多张参考图作为输入并合成新图像，但多参考图生成仍具挑战：模型可能遗漏或重复参考中的主体，或生成多个主体被不自然拼贴的图像。近期工作提出图像生成 Agent，将图像生成模型、推理模型与 Harness（一个规定参考图解读方式、生成执行流程、输出诊断方式与最终图像选取机制的可执行程序）相结合。
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-30-agent-rag-longcontext-candidates.json