5 papers
Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations
Konur Tholl, François Rivest, Mariam El Mezouar +2
Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. ACO applications commonly empl…
FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast
Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3
Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation and Evolution), a staged, p…
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3
Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reason…
Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
Alex Popa, Adrian Taylor, Ranwa Al Mallah
Reinforcement learning techniques are being explored as solutions to the threat of cyber attacks on enterprise networks. Recent research in the field of AI in cyber security has in…
Before You Hand Over the Wheel: Evaluating LLMs for Security Incident Analysis
Sourov Jajodia, Madeena Sultana, Suryadipta Majumdar +2
Security incident analysis (SIA) poses a major challenge for security operations centers, which must manage overwhelming alert volumes, large and diverse data sources, complex tool…