ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning
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 abstract
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “ATLAS: Discovering Agent Strategies through LLM-Guided Abstr” ≈ “AgentCore-8B””
- FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “ATLAS: Discovering Agent Strategies through LLM-Guided Abstr” ≈ “SWE-agent/SWE-agent””
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “ATLAS: Discovering Agent Strategies through LLM-Guided Abstr” ≈ “zhayujie/CowAgent””
- FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “ATLAS: Discovering Agent Strategies through LLM-Guided Abstr” ≈ “NousResearch/hermes-agent””
- FuzzySimilar title/name (fuzzy) · 59%bojieli/ai-agent-book →
“Fuzzy title match (0.73): “ATLAS: Discovering Agent Strategies through LLM-Guided Abstr” ≈ “bojieli/ai-agent-book””
- FuzzySimilar title/name (fuzzy) · 59%iflytek/astron-agent →
“Fuzzy title match (0.73): “ATLAS: Discovering Agent Strategies through LLM-Guided Abstr” ≈ “iflytek/astron-agent””
- LinkedLinked via arxiv author · 85%Ignacio D. Lopez-Miguel →
“ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning”
- LinkedLinked via arxiv author · 85%Andreas Happe →
“ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning”