公开了GitHub代码代理的全流程日志，揭示其工作细节。
AgentLogs: A Dataset for Opening the Black Box of GitHub's Cloud Agent
- 收集30万+任务、54万+会话的详细操作日志
- 记录每步推理、工具调用与资源消耗数据
- 适合研究智能编程代理行为与协作效率
基于生成式AI的软件工程代理正成为真实项目中的常规贡献者。在GitHub上，开发者可将任务分配给Copilot云代理，该代理能自主探索仓库、编辑代码、运行命令、打开或审查拉取请求，并生成每一步操作的详细日志。尽管现有数据集捕捉了代理的输出结果（如自动生成的拉取请求），但其生成过程仍属黑箱。为填补这一空白，我们推出AgentLogs，一个大规模的GitHub代理活动数据集。该数据集包含307,416个代理任务、549,239个代理会话，覆盖扫描的35,810个热门公共仓库（共1,812,362个仓库），以及64,255,174条会话日志条目，完整记录每次代理运行的每一步操作，包括提示词、中间推理、工具调用（如文件编辑、git操作、GitHub交互）和令牌使用情况。通过不仅展示代理产出，还揭示其工作流程，AgentLogs支持对代理行为、效率与成本、任务设计、失败模式及人机协作在智能软件工程中的研究。
原文摘要 · Abstract (English)
Generative AI-based software engineering agents are becoming routine contributors to real-world software projects. On GitHub, developers can assign tasks to the Copilot cloud agent, which autonomously explores the repository, edits code, runs commands, and opens or reviews pull requests, producing a detailed log of every step along the way. While existing datasets capture outcomes of agent contributions, such as agent-authored pull requests, the process by which agents produce these contributions remains largely unexplored. To address this gap, we introduce AgentLogs, a large-scale dataset of agent activity on GitHub. AgentLogs comprises 307,416 agent tasks and 549,239 agent sessions in 35,810 of the 1,812,362 popular public repositories that we scanned, together with 64,255,174 session log entries that record each agent run step by step, including prompts, intermediate reasoning, tool calls (e.g., file edits, git operations, and GitHub interactions), and token usage. By exposing not only what agents contribute but also how they work, AgentLogs enables research on agent behavior, efficiency and cost, task formulation, failure modes, and human-agent collaboration in agentic software engineering.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。