🛰️ Daily AI Frontier
‹ back to 2026-07-22

AgentTrails: Towards Trust and Reuse for Agentic Tasks

Research LLM Agents

Merged summary

TL;DR - AgentTrails converts chronological LLM-agent logs into provenance graphs that expose dependencies among tool calls and artifacts. This representation improves execution comparison, debugging, analysis, and reuse.

  • Models tool calls as computational actions and their inputs and outputs as data artifacts.
  • Aligns multiple executions in a joined quotient graph to identify recurring tools, artifacts, and dependency structures.
  • Supports pattern extraction, downstream analysis, and abstraction of repeated behaviors into skills.
  • Demonstrations on real-world trajectories reveal hidden dependencies and recurring tool-use patterns obscured by chronological logs.

Sources (1)

AgentTrails: Towards Trust and Reuse for Agentic Tasks

arXiv cs.DB Eden Wu, Sonia Castelo, Yurong Liu, Cláudio T. Silva, Juliana Freire 2026-07-21 arXiv:2607.18816

TL;DR - AgentTrails converts chronological LLM-agent logs into provenance graphs that expose dependencies among tool calls and artifacts. This representation improves execution comparison, debugging, analysis, and reuse.

  • Models tool calls as computational actions and their inputs and outputs as data artifacts.
  • Aligns multiple executions in a joined quotient graph to identify recurring tools, artifacts, and dependency structures.
  • Supports pattern extraction, downstream analysis, and abstraction of repeated behaviors into skills.
  • Demonstrations on real-world trajectories reveal hidden dependencies and recurring tool-use patterns obscured by chronological logs.
item →