发表机构
New York University（纽约大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大语言模型驱动代理轨迹掩盖数据依赖限制开发人员理解等问题，提出AgentTrails系统，将原始轨迹转换为结构化溯源图，支持执行比较、模式提取等，能揭示隐藏依赖、对齐不同执行并展现重复工具使用模式。
AI 中文摘要
由大语言模型驱动的代理通过调用工具、查询数据库、执行代码和操作中间工件来处理复杂任务。这些代理的轨迹通常按时间顺序存储为日志，掩盖了潜在的数据流，即其操作与创建和操作的工件之间的依赖关系。这限制了开发人员理解代理轨迹、比较执行情况、调试故障和重用计算的能力。我们提出了AgentTrails，一个用于代理溯源和理解的原型系统。它将原始轨迹转换为结构化的溯源图，将工具调用建模为计算操作，将输入和输出建模为数据工件。该系统通过将多个溯源图放在共享画布上并构建联合商图来支持执行比较，该联合商图可对齐不同轨迹中的重复工具、工件和依赖结构。在此表示之上，AgentTrails支持模式提取、下游分析和技能抽象。我们在真实世界的代理轨迹上演示了AgentTrails，表明它揭示了隐藏的依赖关系，对齐了不同的执行情况，并揭示了超越时间顺序日志的重复工具使用模式。
英文摘要
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.
Comments4 pages, 4 figures. Short paper accepted at the Workshop on Systems for Data-centric Agents with Human-in-the-loop (DASHSys 2026), co-located with VLDB 2026
