AI 自己改自己的设计流程，海报质量反超商业系统
现在的 AI 做「把论文变成海报」这类长任务，流程是写死的：模型按固定步骤跑，不会从失败里学。这篇让 AI 自己改自己的流程：一个「元优化器」盯着每次生成的反馈，指挥代码 agent 调整下一步怎么做，再跑、再改，循环往复。在 100 篇论文的测试集上，它拿到 78.32 分，比商业系统 Claude Design 高 7.45 分；换不同底层模型，这套自改流程都能把平均分从 55 拉到 67。全程自动跑完一篇海报只要 40 分钟、成本不到 3 美元，人类盲评里它也是首选。它不是你明天就能用的工具，但指向一个更本质的变化：AI 不再只是执行者，开始当自己的流程设计师。
📄 原文摘要(英文)
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors and accumulate reusable experience through empirical exploration to drive recursive self-improvement, existing paradigms remain static and fall short of this capability. In this paper, we present AutoDesign, a framework that aligns with human design priors, where a meta-harness optimizer guides a code agent to recursively improve harness based on rollout feedback. To instantiate and evaluate this framework, we focus on the academic paper-to-poster generation task and introduce PosterBench, comprising a 100-paper Main Track spanning five disciplines and PosterBench-mini, a shared 10-paper subset for controlled evaluation. On the PosterBench Main Track, AutoDesign achieves the highest score of 78.32, surpassing the closed-source commercial system Claude Design by 7.45 points. Across seven controlled code-agent-model configurations, integrating the learned DesignHarness consistently improves performance, increasing the average PosterBench Score from 54.99 to 67.39 (+12.4%). In a fully autonomous long-horizon loop, it executes 253 tool calls and 11 editing turns within 40 minutes for under $3, reaching average conference-poster quality in human evaluation. A system-blind human study further demonstrates that AutoDesign achieves the highest human preference among evaluated systems.