研究人员推出了ClawGym，一个旨在简化能够处理涉及本地文件和工具的多步工作流的个人代理开发的框架。该框架包含一个包含13.5K个任务的合成数据集，名为ClawGym-SynData，以及一个用于评估的200个实例的基准。此外，ClawEnvKit提供了一个自动化管道，用于为这些爪式代理的训练和评估生成多样化且经过验证的环境，显著减少了先前所需的手动工作。 AI
影响 为开发和评估复杂的个人代理提供了可扩展的框架和自动化工具，有可能加速代理的研究和部署。
排序理由 该集群描述了介绍代理开发和环境生成框架和工具的新学术论文。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2604.26904v1 Announce Type: new Abstract: Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, esp…
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training…
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training…
arXiv:2604.18543v2 Announce Type: replace-cross Abstract: Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of…