Automata from Agent Traces: Failure and Next-Step Prediction

  • 类型:arxiv
  • 标识:2608.23670
  • 链接:https://arxiv.org/abs/2608.23670
  • 主分类:agent
  • 形态:application
  • TLDR:LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtime monitoring that deployment requires. Existing approaches operate per-trace or success-only, so they miss the cross-run topology that links next-step and failure prediction. To recover that shared structure, we collapse an entire trace corpus into a single, compact finite-state machine (FSM) that serves as a structural substrate for the otherwise unpredictable behavior of LLM agents. Across twelve public datasets, the FSMs are compact (7-43 st
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-08-27-agent-rag-longcontext-candidates.json