When the Governor Becomes the Disturbance: Control-Generated Disturbance and Cost-Aware Backoff in Governed Tool-Using Agents

cs.AI, cs.MA

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: Includes ancillary experimental data and a Python script for reproducing numerical summaries. Code: https://github.com/CriticalAttentionSystems/CASAgentGovernor

Code: https://github.com/CriticalAttentionSystems/CASAgentGovernor

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• IRAM-Omega-Q: A Computational Framework for Uncertainty Regulation in Adaptive Agents
• When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency
• Intermittent Control Is Not Diluted Control: A Switching Effect in Artificial Agency
• The Autonomy Tax: Defense Training Breaks LLM Agents
• CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
• Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems