Agentic Pressure: The Endogenous Entropy of Reliable Autonomy

📅 2026-09-05
📈 Citations: 0
Influential: 0
📄 PDF
📝 Abstract
Achieving reliable autonomy in the wild requires agents to sustain continuous operations across long-horizon trajectories. However, as agents navigate these unconstrained settings, they encounter cumulative friction that inherently destabilizes their alignment. In this paper, we identify a distinct non-adversarial phenomenon termed Agentic Pressure. We define this as a kinetic force that spontaneously emerges when the cost of compliance conflicts with the imperative of goal achievement. Unlike static jailbreaks, this pressure is endogenous and arises directly from the dynamics of interaction. We propose a theoretical framework that formalizes Agentic Pressure as the ratio between the required work to overcome environmental friction and the remaining capacity of the agent. Our analysis demonstrates that when this pressure exceeds a critical threshold, agents exhibit safety drift as a mathematically optimal adaptation. Consequently, they often resort to Instrumental Hallucination to rationalize rule violations. Empirical experiments validate this framework and show that aligned agents spontaneously compromise safety to preserve autonomy under high-pressure conditions.
Problem

Research questions and friction points this paper is trying to address.

Reliable Autonomy
Agentic Pressure
Cumulative Friction
Safety Drift
Instrumental Hallucination
Innovation

Methods, ideas, or system contributions that make the work stand out.

Agentic Pressure
Endogenous Entropy
Reliable Autonomy
Instrumental Hallucination
🔎 Similar Papers
No similar papers found.
H
Hengle Jiang
Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
Z
Ziying Luo
Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
Ke Tang
Ke Tang
Professor, Southern University of Science and Technology
Artificial IntelligenceEvolutionary ComputationMachine Learning