AutoDesign: Meta-Harness Optimisation for Long-Horizon Agentic Design

ArticleYaxin 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 LiResearch

Researchers introduce AutoDesign, a framework that converts multimodal sources such as academic papers into structured visual formats like conference posters. A meta-harness optimiser guides a code agent to recursively improve its harness based on rollout feedback.

Key points

  1. AutoDesign uses a meta-harness optimiser to enable recursive self-improvement of a code agent through empirical rollout feedback.
  2. The researchers introduced PosterBench, an evaluation benchmark containing 100 papers across five disciplines, alongside a 10-paper subset called PosterBench-mini.
  3. On the PosterBench Main Track, AutoDesign scored 78.32, outperforming the commercial tool Claude Design by 7.45 points.
  4. Integrating the learned DesignHarness across seven code-agent model setups improved the average score from 54.99 to 67.39 (+12.4%).
  5. During an autonomous run, the agent executed 253 tool calls and 11 editing turns in under 40 minutes for less than $3.
  6. A blind human evaluation ranked AutoDesign highest in human preference, confirming average conference-poster quality.

Why it matters

Automating complex graphic layout tasks requires long-horizon planning and iterative refinement. AutoDesign demonstrates that dynamic harness optimisation allows autonomous agents to deliver viable, publication-ready design outputs efficiently and at low operational cost.

Analysis

The research highlights a shift from rigid agent architectures toward self-improving execution environments. By iteratively tuning the harness based on empirical feedback, the agent significantly narrows the gap with commercial systems. Achieving acceptable conference poster quality within 40 minutes and under $3 demonstrates the practical feasibility of autonomous agentic design pipelines.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link: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

    AutoDesign: Meta-Harness Optimisation for Long-Horizon Agentic Design

    Researchers introduce AutoDesign, a framework that leverages autonomous code agents to transform multimodal content into structured media outputs like conference posters. A meta-harness optimiser recursively improves the agent harness using rollout feedback, outperforming existing commercial systems.

    AI & LLMs· Research

  • Article:Jiaqi Liu et al.

    AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

    A research team led by Jiaqi Liu introduces AutoResearchClaw, an autonomous multi-agent research pipeline. Moving away from rigid linear workflows, the system implements iterative error recovery, verifiable reporting, and adaptable human intervention modes. On the ARC-Bench benchmark, it outperforms AI Scientist v2 by 54.7%.

    AI & LLMs· Research

  • Article:Shuai Shao, Kangning Zhang, Qingyao Li, Shijian Wang, Hao Wang, Wenxiang Jiao, Yuan Lu, Yi Guo, Weiwen Liu, Weinan Zhang

    Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

    Researchers introduce Harness-R1, a framework that trains a dedicated agent to adapt and patch the runtime harness of LLM agents based on failure logs. Using online reinforcement learning, a separate 9B model learns to generate executable patches for context handling, tool mediation, and error recovery to directly improve task completion.

    AI & LLMs· Research

  • Link:Powerformer, Inc.

    OpenDesign: Local Open-Source Alternative to Claude Design

    OpenDesign is an open-source, local-first AI design workspace released under the Apache-2.0 licence, positioned as an alternative to proprietary cloud platforms like Claude Design. It connects existing local coding agents into a structured design engine for generating prototypes, dashboards, slides, and HTML video.

    AI & LLMs· Tool

  • Article:Mehdi Allahyari

    The Harness Beats the Model: Demystifying Agent Harness Engineering

    Following prompt and context engineering, harness engineering marks the third wave in developing autonomous AI systems. Mehdi Allahyari explains why the software infrastructure wrapping an LLM matters more than raw model scale for reliability and self-correction.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.