发表机构
The University of Osaka（大阪大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对AI编码智能体行为难以从日志理解的问题，提出Agent ATO工具，从控制台日志提取交互并按类型分类可视化时间线，支持过滤视图，帮助开发者检查比较智能体动作。
AI 中文摘要
AI 编码智能体正逐渐成为开发者工作流程的一部分，但仅从最终的代码变更中很难理解其行为。在任务执行过程中，智能体通过一系列动作与软件仓库交互，例如搜索文件、阅读代码、编辑程序以及运行测试或构建命令。这些交互以及 token 使用情况通常记录在控制台日志中，但原始日志难以供开发者检查。在本文中，我们提出了 Agent ATO（智能体轨迹观察器），一种从控制台日志中可视化 AI 编码智能体交互时间线的工具。Agent ATO 提取智能体交互，按命令或工具类型对其分类，并将其可视化为时间线。除了全交互时间线外，Agent ATO 还提供过滤后的时间线，这些时间线强调文件发现、文件阅读、文件编辑和执行，同时保留周围上下文。我们通过两个修复任务中的选定运行来展示 Agent ATO 如何帮助开发者检查和比较智能体动作。未来工作将把 Agent ATO 应用于更多智能体、任务和开发环境，并评估其是否能减少比较轨迹所需的工作量。
英文摘要
AI coding agents are becoming part of developers' workflows, but their behavior is difficult to understand from final code changes alone. During a task, agents interact with software repositories through sequences of actions such as searching for files, reading code, editing programs, and running tests or build commands. These interactions, together with token usage, are often recorded in console logs, but raw logs are difficult for developers to inspect. In this paper, we propose Agent ATO (Agentic Trajectory Observer), a tool for visualizing AI coding agent interaction timelines from console logs. Agent ATO extracts agent interactions, classifies them by command or tool type, and visualizes them as timelines. In addition to an all-interaction timeline, Agent ATO provides filtered timelines that emphasize file discovery, file reading, file editing, and execution while preserving surrounding context. We illustrate how Agent ATO may help developers inspect and compare agent actions using selected runs from two repair tasks. Future work will apply Agent ATO to more agents, tasks, and development environments, and will evaluate whether it reduces the effort needed to compare trajectories.
CommentsVISSOFT 2026 NIER Track
