AutoDesign：面向长时程智能体设计的元编排优化

摘要

将多模态源转化为精简且结构化的媒体输出，从根本上可以概念化为一个以模型-框架（model-harness）系统为核心的长周期智能体过程。理想情况下，框架系统应当与人类设计先验保持一致，并通过经验性探索积累可复用的经验，从而驱动递归式自我改进；然而，现有范式仍是静态的，无法实现这一能力。在本文中，我们提出AutoDesign，一个与人类设计先验对齐的框架，其中元框架优化器（meta-harness optimizer）引导代码智能体基于回滚反馈（rollout feedback）递归地改进框架。为实例化和评估该框架，我们聚焦于学术论文到海报生成任务，并引入PosterBench，该基准包含覆盖五个学科、共100篇论文的主轨（Main Track），以及PosterBench-mini——一个用于受控评估的10篇论文共享子集。在PosterBench主轨上，AutoDesign取得了78.32的最高分，超越闭源商业系统Claude Design达7.45分。在七种受控代码智能体-模型配置中，集成学习得到的DesignHarness持续提升性能，将平均PosterBench得分从54.99提升至67.39（+12.4%）。在完全自主的长周期循环中，该系统在40分钟内、成本不到3美元的条件下执行了253次工具调用和11轮编辑，在人工评估中达到平均会议海报质量。一项系统盲测人工研究进一步表明，AutoDesign在评估系统中获得了最高的人类偏好。

English

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.