Cognitive Friction: A Decision-Theoretic Framework for Bounded Deliberation in Tool-Using Agents
This addresses systematic failure modes like excessive tool use and prolonged deliberation in networked environments, with incremental improvements in decision-making for autonomous agents.
The paper tackles the problem of autonomous tool-using agents making decisions on when to stop querying information sources and act, by proposing the Triadic Cognitive Architecture (TCA) framework, which reduces time-to-action while improving resource outcomes without degrading accuracy, gaining 36 viability points in one simulation and 33 integrity points in another over greedy baselines.
Autonomous tool-using agents operating in networked environments must decide which information source to query and when to stop querying and act. Without principled bounds on information-acquisition costs, unconstrained agents exhibit systematic failure modes: excessive tool use under congestion, prolonged deliberation under time decay, and brittle behavior under ambiguous evidence. We propose the Triadic Cognitive Architecture (TCA), a unified decision-theoretic framework that formalizes these failure modes through the concept of Cognitive Friction. By synthesizing nonlinear filtering theory, congestion-dependent cost dynamics, and HJB optimal stopping, we model deliberation as a stochastic control problem over a joint belief-congestion state space, where information acquisition is explicitly priced by tool-dependent signal quality and live network load. Rather than relying on arbitrary heuristic stop-tokens or fixed query budgets, TCA derives an HJB-inspired stopping boundary and instantiates a computable rollout-based approximation of belief-dependent value-of-information with a net-utility halting condition. We validate the framework on two controlled simulation environments, the Emergency Medical Diagnostic Grid (EMDG) and the Network Security Triage Grid (NSTG), designed to isolate key decision-theoretic quantities under reproducible conditions. TCA reduces time-to-action while improving resource outcomes without degrading accuracy: over greedy baselines, TCA gains 36 viability points in EMDG and 33 integrity points in NSTG. Ablations confirm joint optimization of selection and stopping is essential; stopping rules alone recover at most 4 viability points. A sensitivity sweep over alpha, beta, lambda_S shows stable accuracy and interpretable tradeoffs; an empirical sweep over eta in {0, 0.1, 0.3, 0.5} confirms eta=0 is optimal on EMDG trajectories under high temporal urgency.