AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
2026-08-13 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceComputation and Language
AI summaryⓘ
The authors created AutoDesign, a system that improves itself over time when turning academic papers into posters by learning from past attempts. They tested it using a new benchmark called PosterBench, which includes papers from multiple fields. AutoDesign did better than other systems, including a commercial one called Claude Design, and was preferred by humans in a blind study. It can work on its own for a long time, making many edits efficiently and at low cost. This shows that their method of self-improving design tools can create higher-quality academic posters.
multimodal generationagentic processmeta-optimizationrecursive improvementacademic poster generationbenchmark datasetshuman evaluationcode agentstool use in AIself-improving systems
Authors
Yaxin Luo, Haobin Jiang, Jialv Zou, Xu Huang, Wenhao Yan, Haodong Li, Zhengrong Yue, Jing Li, Xiaofu Chen, Xiaohan Zhao, Jiacheng Liu, Jiacheng Cui, Zhiqiang Shen, Xiaotong Li
Abstract
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.