Tool-mediated LLM agents with deterministic tools and a machine-checked Lyapunov certificate achieve stable control in cyber defense, reducing attacker game value by 59% on real attack graphs.
Actsafe: Active exploration with safety constraints for reinforcement learning.arXiv
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A robust adaptive MPC framework for nonlinear systems with bounded disturbances uses Gaussian process models and contraction metrics to guarantee recursive feasibility, robust constraint satisfaction, and convergence with high probability.
citing papers explorer
-
Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber Defense
Tool-mediated LLM agents with deterministic tools and a machine-checked Lyapunov certificate achieve stable control in cyber defense, reducing attacker game value by 59% on real attack graphs.
-
A robust and adaptive MPC formulation for Gaussian process models
A robust adaptive MPC framework for nonlinear systems with bounded disturbances uses Gaussian process models and contraction metrics to guarantee recursive feasibility, robust constraint satisfaction, and convergence with high probability.