一项名为Workflow-GYM的新基准已被引入，用于评估AI代理在专业软件环境中的复杂、长周期任务。目前的AI代理在处理这些真实世界工作流程方面表现出显著的局限性，即使是最先进的模型成功率也仅略高于30%。研究突出了工作流程执行不一致、错误传播以及对专业软件理解不足等问题，表明需要对代理能力进行重大改进。 AI
影响 强调了当前AI代理在专业任务中的显著局限性，为代理AI的未来研究指明方向。
排序理由 该集群包含一篇介绍AI代理评估新基准的研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.11042v1 Announce Type: new Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-…
Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows acros…
Current AI agents struggle with long-horizon professional GUI workflows, achieving low success rates due to issues with workflow consistency and domain-specific software understanding.