将智能体任务轨迹转化为可分析的依赖图谱，提升可理解性与复用性。
AgentTrails: Towards Trust and Reuse for Agentic Tasks
- 把智能体操作日志转为带数据依赖的结构化图谱
- 通过图对比发现重复工具调用模式和隐藏依赖关系
- 适合开发人员调试、分析智能体行为及复用计算流程
基于大模型的智能体通过调用工具、查询数据库、执行代码和操作中间产物来完成复杂任务。这些智能体的行为轨迹通常以时间顺序日志形式存储，掩盖了背后的数据流——各操作与生成/修改产物之间的依赖关系。这限制了开发者对智能体行为的理解、执行对比、故障排查以及计算复用。我们提出 AgentTrails，一个用于智能体溯源与意义建构的原型系统。AgentTrails 将原始轨迹转化为结构化的溯源图，将工具调用建模为计算动作，输入输出视为数据产物。系统支持在共享画布上并列多个溯源图，并构建联合商图，对齐不同轨迹中重复出现的工具、产物和依赖结构。在此基础上，支持模式提取、下游分析与技能抽象。我们在真实智能体轨迹上验证了该系统，结果表明它能揭示隐藏依赖、对齐分歧执行路径，并发现超越时间日志的重复工具使用模式。
原文摘要 · Abstract (English)
LLM-powered agents increasingly tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts. These agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow -- the dependencies between their actions and the artifacts they create and manipulate. This limits developers' ability to understand the agents' trails, compare executions, debug failures, and re-use the computations. We present AgentTrails, a prototype system for agent provenance and sensemaking. AgentTrails converts raw trajectories into structured provenance graphs, where tool calls are modeled as computational actions and inputs and outputs as data artifacts. The system supports the comparison of executions by placing multiple provenance graphs on a shared canvas and constructing a joined quotient graph that aligns recurring tools, artifacts, and dependency structures across trajectories. On top of this representation, AgentTrails supports pattern extraction, downstream analysis, and skill abstraction. We demonstrate AgentTrails on real-world agent trajectories, showing that it reveals hidden dependencies, aligns divergent executions, and surfaces recurring tool-use patterns beyond chronological logs.
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。