cs.AINov 9, 2026

A Bifurcation-Theoretic Framework for the Controllability of Emergent Intelligent Systems

Authors: Hao Li, Shaowen Lu

Organizations: Aufkenn Technologies Co., Ltd., Ningbo, China · Northeastern University, Shenyang, China

Abstract

Real-world intelligent systems must reconcile two demands: the adaptability conferred by emergence and the steerability required for accountable deployment. We show that these demands are governed by two distinct bifurcations on the same object and that, consequently, increased capability does not imply increased controllability. Emergence is a bifurcation of the capability variable SS, with criterion Γ:=F′(0)>1Γ:=\mathcal F'(0)>1 equivalent to the existence of a unique positive stable fixed point of a self-consistency equation, following solely from the concavity of F\mathcal F. Controllability is a bifurcation of the permission variable cc, whose dynamics include an erosion term and exhibit a saddle-node fold with hysteresis as the gate criterion ρ∗ρ^\ast crosses unity. Three quantitative results follow: the critical exponent distinguishes families rather than classifying the transition; the gating-cost bound K(M)∝log⁡(1+M)K(M)\propto\log(1+M) grows with scope, not capability; and the fold threshold is γc≈4μκγ_c\approx4μκ. Calibrated in both directions, the criteria reproduce the two-dimensional Ising transition, admit two true-feedback order parameters, and reject nine candidate quantities, supporting the conclusion that the order parameter is geometric rather than capability-related. Since permission cannot be endogenized and no deployed system has been measured to satisfy Γ>1Γ>1 and ρ∗>1ρ^\ast>1 simultaneously, increased capability does not imply controllability.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. The Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering

    Oct 19, 2026Hao Li, Minghui Ren, Shaowen LuInverse DesignEmergent Behavior in Multi-Agent Systems

  2. Trajectory-Aware Node Contributions and the Limits of Static Controllability

    Jun 2, 2026Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge

  3. A Mathematical Theory of Agency and Intelligence

    Feb 26, 2026Wael Hafez, Chenan Wei, Rodrigo Pena +2AI Agent Monitoring