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

arXiv: https://arxiv.org/abs/2610.09037 · HTML: https://mlsanity.com/paper/2610.09037/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution](https://mlsanity.com/paper/2602.07918/) (2026)
- [The Autonomy Tax: Defense Training Breaks LLM Agents](https://mlsanity.com/paper/2603.19423/) (2026)
- [Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon](https://mlsanity.com/paper/2309.11453/) (2023)
- [IRAM-Omega-Q: A Computational Framework for Uncertainty Regulation in Adaptive Agents](https://mlsanity.com/paper/2603.16020/) (2026)
- [When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency](https://mlsanity.com/paper/2606.30975/) (2026)
- [Intermittent Control Is Not Diluted Control: A Switching Effect in Artificial Agency](https://mlsanity.com/paper/2607.17432/) (2026)

## Abstract (arXiv)

Supervisory governors can interfere with the tool-using agents they regulate. We study this possibility in a controlled file-recovery environment where increases in regulatory intensity trigger experimentally imposed tool failures. A cost-blind governor can turn these failures into persistent blocking that prevents task completion. We compare this governor with a backoff rule that reduces intervention probability using a moving average of known induced events. On a hand-coded stochastic-policy agent, the failure pattern appears under both result replacement and execution of corrupted tool arguments. For the persistent policy, adaptive backoff improves completion relative to a fixed weak governor with approximately matched intervention frequency. A Gemini 2.5 Flash experiment comprising 576 episodes across 6 tasks also shows reduced blocking and improved completion under backoff; among the tested settings, intermediate backoff strength achieves the highest observed aggregate success. These results identify an interaction between intervention cost and persistent action blocking, together with a possible mitigation. The cost mechanisms are imposed and their induced events are directly observable to the backoff rule; applicability beyond this controlled environment remains an empirical question.