# Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute

arXiv: https://arxiv.org/abs/2605.15377 · HTML: https://mlsanity.com/paper/2605.15377/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Ctrl-Z: Controlling AI Agents via Resampling](https://mlsanity.com/paper/2504.10374/) (2025)
- [Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols](https://mlsanity.com/paper/2510.09462/) (2025)
- [Async Control: Stress-testing Asynchronous Control Measures for LLM Agents](https://mlsanity.com/paper/2512.13526/) (2025)
- [How to evaluate control measures for LLM agents? A trajectory from today to superintelligence](https://mlsanity.com/paper/2504.05259/) (2025)
- [Control Tax: The Price of Keeping AI in Check](https://mlsanity.com/paper/2506.05296/) (2025)
- [Combining Cost-Constrained Runtime Monitors for AI Safety](https://mlsanity.com/paper/2507.15886/) (2025)

## Built on by (most cited first, 6 of 6)

- [Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages](https://mlsanity.com/paper/2607.06596/) (2026)
- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [Reliability Theory for AI Control](https://mlsanity.com/paper/2609.26419/) (2026)
- [Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles](https://mlsanity.com/paper/2608.16190/) (2026)
- [Improving scalable oversight with co-trained monitors](https://mlsanity.com/paper/2609.36049/) (2026)
- [Towards a Unified Misuse Monitoring Benchmark](https://mlsanity.com/paper/2610.07089/) (2026)

## Abstract (arXiv)

As AI systems are increasingly deployed in autonomous agentic settings at scale, it is important to ensure the actions they take are safe and aligned with user intent. Monitoring agent actions is a key safety mechanism, yet reliable monitors remain difficult to build and the scale of these systems makes human oversight impractical. We show that combining signals from diverse monitors into an ensemble improves detection of misaligned actions. We build 12 GPT-4.1-Mini monitors using both prompting and fine-tuning strategies. We evaluate them on coding tasks where candidate solutions pass standard tests but fail on adversarial inputs. In this setting, diverse ensembles outperform both individual monitors and homogeneous ensembles. Our best 3-monitor ensemble achieves 2.4x greater detection performance gain compared to an ensemble composed of three identical monitors, with the same ensemble performing strongly on an independent dataset. We contend that these results show that diversity - not scale - drives gains. The best ensembles combine strong individual performance with low correlation between monitors. Furthermore, fine-tuned monitors appear in every top-performing ensemble and maintain this advantage on out-of-distribution attack types, suggesting that fine-tuning enables detection capabilities that prompting alone does not elicit. These results support ensemble monitoring as a practical AI control strategy for safety gains at reasonable inference costs.