ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning

Excerpt

arXiv:2608.14352v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents are increasingly used for complex tasks such as software testing and cybersecurity assessment. While these agents demonstrate impressive capabilities, their behavior is difficult to understand, explain, and analyze. Existing evaluations focus mainly on task success and execution traces, offering limited insight into the strategies employed by the agent. We present ATLAS (Automata Learning for Agent Trajecto