Metraipolis › archive › dc_6ecdc23e8109

ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning — arXiv:2608.14352

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14352
License (as archived)
CC0-1.0
Archived
2026-10-19T02:30:52.017Z
SHA-256 of the archived text
a028acff8ba7e621ef611838160fe66c7e7ffe464ba155bd7109136a841505af
Stable URL of this page
https://metraipolis.com/documento/dc_6ecdc23e8109

How to cite

ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning — arXiv:2608.14352 — arXiv (en), https://arxiv.org/abs/2608.14352 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ecdc23e8109 (Metraipolis archive dc_6ecdc23e8109, sha256 a028acff8ba7e621ef611838160fe66c7e7ffe464ba155bd7109136a841505af)
BibTeX
@misc{dc6ecdc23e8109,
  title = {ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning — arXiv:2608.14352},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14352},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ecdc23e8109; sha256 a028acff8ba7e621ef611838160fe66c7e7ffe464ba155bd7109136a841505af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14352. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 Trajectory Analysis and Strategy Discovery), an approach for recovering interpretable behavioral models from agent trajectories. ATLAS combines trace abstraction with automata learning to infer finite-state models that capture observed agent-environment interaction strategies. These models provide human-interpretable insights and support automated analyses of recurring behaviors, decision points, successful task-completion paths, and failure loops. As a proof of concept, we apply ATLAS to trajectories generated by an LLM-based penetration-testing agent. The resulting models expose high-level behavioral strategies for exploiting vulnerable machines that are difficult to identify from raw execution traces alone. We discuss how learned behavioral models can support explainability, model-guided exploration, auditing, and analysis of agentic systems. We further demonstrate symbolic model-based knowledge transfer from powerful frontier models to compact language models. In addition, we show how model transformations can derive concise explanations of agent behavior in a penetration-testing case study comprising 12 vulnerable machines. ATLAS highlights a new opportunity for model-driven engineering: transforming agent trajectories into explicit behavioral models that enable systematic understanding and analysis of otherwise opaque AI agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG).
Categorie arXiv: Software Engineering (cs.SE) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14352 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:26:17.838Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).