This article develops a unified account of Mediative Fuzzy Logic, from its type-1 foundations to type-2, type-3, and quantum extensions. It characterizes the mediative operator, models mediative truth values, and introduces a propositional system, establishing its soundness and paraconsistency.
The article details a 7-layer AI governance stack built over six months to manage 53 autonomous AI agents in production without incidents. This system allows agents to make real decisions safely across various family management domains.
Credo introduces a novel framework for declaratively controlling LLM pipelines, representing semantic state as beliefs and regulating behavior through policies. This design aims to enhance the adaptability, auditability, and composability of agentic AI systems by moving away from brittle imperative control loops.
This paper introduces a communication-efficient reinforcement learning approach where a single policy learns both control inputs and timing decisions, secured by a pointwise Lyapunov safety shield. A run-time assurance layer overrides the policy to provide strictly stronger safety guarantees and achieve significantly higher mean inter-sample intervals on various systems.
The content argues that AI agents need an "operating system" rather than just a harness to ensure reliable, controlled work, focusing on aspects like separating execution from checking, explicit unknowns, and auditability. It introduces XRefKit as an example of this approach, aiming for controlled AI work over full autonomy.