pagarsky/agent-trace

AgentTrace是一个关于工具使用语言模型代理跟踪的开源数据集，包含执行遥测数据。每个跟踪记录包括模型生成步骤、工具调用、实时计时、操作系统级资源使用情况、工具输入和输出、推理内容以及可重复性元数据。数据集还包含收集代码、分析脚本和确定性NL2Bash固定装置，用于重放本地命令行任务。数据集的文件包括来自MBPP测试分割和NL2Bash/InterCode策划的任务，涉及不同模型版本的跟踪记录。

AgentTrace is an open dataset of tool-using language-model agent traces with execution telemetry. Each trace records model-generation steps, tool calls, wall-clock timing, OS-level resource usage, tool inputs and outputs, reasoning content, and reproducibility metadata. The repository contains the dataset, collection code, analysis scripts, and the deterministic NL2Bash fixture needed to replay the local command-line tasks. The dataset files include tasks from MBPP test split and NL2Bash/InterCode curated, involving trace records of different model versions.