ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning
Source
Ignacio D. Lopez-Miguel, Andreas Happe, J\"urgen Cito, Ezio Bartocci, Bettina K\"onighofer, Martin Tappler
Author
Ignacio D. Lopez-Miguel, Andreas Happe, J\"urgen Cito, Ezio Bartocci, Bettina K\"onighofer, Martin Tappler
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Trace dumps tell you what an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → did once; a learned automaton tells you what it tends to do. That is a practical handle for auditing agent behavior before trusting it with a task.
articleAgentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration TestingIsrat Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha
articleSupporting Industrial Test-Failure Analysis with LLM-Based Systems: An Experience ReportEric Jansson, Per Strandberg, Thomas S\"orensen, Eduard Paul Enoiu, Wasif Afzal
articleOpenDiscoveryTrace: Process Traces for Evaluating AI Scientist WorkflowsAayam Bansal, Keertan Balaji