4 papers
Strategies in POMDPs with Stage Duration
Ivan Novikov
Partially observable Markov decision processes (POMDPs) with stage duration provide a framework for approximating continuous-time behavior by scaling transition probabilities with…
Asymptotic Value in Zero-Sum Stochastic Games with Vanishing Stage Duration and Public Signals
Ivan Novikov
We study -discounted zero-sum games as the discount factor approaches (that is, the players are more and more patient), in the context of games with stage duration. In…
MLPMoE: Zero-Shot Architectural Metamorphosis of Dense LLM MLPs into Static Mixture-of-Experts
Ivan Novikov
Large Language Models (LLMs) are predominantly deployed as dense transformers, where every parameter in every feed-forward block is activated for every token. While architecturally…
A2AS: Agentic AI Runtime Security and Self-Defense
Eugene Neelou, Ivan Novikov, Max Moroz +15
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates mode…