The Triadic Cognitive Architecture: Bounding Autonomous Action via Spatio-Temporal and Epistemic Friction
2026-03-31 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors explain that current AI agents often act without understanding time, network limits, or how information flows, causing problems like overusing tools or taking too long to decide. They introduce the Triadic Cognitive Architecture (TCA), a new math-based way to model AI thinking by using ideas from physics and control theory, which helps the AI decide when to stop gathering information more logically. They test this approach in a medical diagnosis simulation and show that their method makes quicker, better decisions without losing accuracy compared to simpler methods. This work helps AI agents behave more thoughtfully and efficiently in complex environments.
Large Language ModelsCognitive FrictionStochastic ControlOptimal ControlRiemannian GeometryNonlinear FilteringValue of InformationStopping BoundaryEmergency Medical Diagnostic Grid
Authors
Davide Di Gioia
Abstract
Current autonomous AI agents, driven primarily by Large Language Models (LLMs), operate in a state of cognitive weightlessness: they process information without an intrinsic sense of network topology, temporal pacing, or epistemic limits. Consequently, heuristic agentic loops (e.g., ReAct) can exhibit failure modes in interactive environments, including excessive tool use under congestion, prolonged deliberation under time decay, and brittle behavior under ambiguous evidence. In this paper, we propose the Triadic Cognitive Architecture (TCA), a unified mathematical framework that grounds machine reasoning in continuous-time physics. By synthesizing nonlinear filtering theory, Riemannian routing geometry, and optimal control, we formally define the concept of Cognitive Friction. We map the agent's deliberation process to a coupled stochastic control problem where information acquisition is path-dependent and physically constrained. Rather than relying on arbitrary heuristic stop-tokens, the TCA uses an HJB-motivated stopping boundary and instantiates a rollout-based approximation of belief-dependent value-of-information with a net-utility halting condition. Through empirical validation in a simulated Emergency Medical Diagnostic Grid (EMDG), we demonstrate that while greedy baselines over-deliberate under latency and congestion costs, the triadic policy reduces time-to-action while improving patient viability without degrading diagnostic accuracy in this environment.