Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute

• URL: http://arxiv.org/abs/2605.15377v2
• Date: Mon, 18 May 2026 07:58:13 GMT
• Title: Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute
• Abstract summary: We show that combining signals from diverse monitors into an ensemble improves detection of misaligned actions.<n>We build 12 GPT-4.1-Mini monitors using both prompting and fine-tuning strategies.<n>Our best 3-monitor ensemble achieves 2.4x greater detection performance gain compared to an ensemble composed of three identical monitors.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control [59.15149762610843]
  Reinforcement learning systems are significantly more complex than other machine learning paradigms.<n>Despite advances in individual algorithmic components, their functional interdependencies remain underexplored.<n>We propose ROSER, an RL framework that coordinates three critical dimensions: Model-based Representation, Optimization Stability, and Experience Replay.
  arXiv  Detail & Related papers  (2026-08-07T10:38:31Z)
• $D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing [63.49501120848927]
  Safety monitoring for large language models (D-LLMs) remains largely unexplored.<n>We propose $D2$-Monitor, a bi-level safety monitor for D-LLMs.<n>$D2$-Monitor adopts a lightweight probe as an always-on monitor to jointly estimate hesitation and perform base classification.
  arXiv  Detail & Related papers  (2026-05-25T14:22:21Z)
• Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning [56.64821510576244]
  We formulate cooperative active observation as a decentralized control problem in which multiple robots adjust their motion to directly optimize monitoring accuracy under partial observability.<n>We propose a learning-based framework for cooperative policies from decentralized observations using multi-agent reinforcement learning (MARL), supported by an architecture that handles variable numbers of humans and temporal dependencies.
  arXiv  Detail & Related papers  (2026-04-25T07:20:15Z)
• SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation [55.67206878777881]
  We propose SMFormer, a framework integrating more reliable self-supervision guided by the Vision Foundation Model (VFM) and data augmentation.<n> SMFormer achieves state-of-the-art (SOTA) performance among self-supervised methods and even competes on par with supervised ones.
  arXiv  Detail & Related papers  (2026-04-11T13:56:41Z)
• Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory [11.144603446849674]
  Chain-of-thought (CoT) monitors are systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest.<n>In this paper, we show that non-zero mutual information between CoT and output is a necessary but not sufficient condition for CoT monitorability.
  arXiv  Detail & Related papers  (2026-02-20T15:50:30Z)
• Monitoring Monitorability [7.993120960324396]
  We propose three evaluation archetypes (intervention, process, and outcome-property) and a new monitorability metric.<n>We compare the monitorability of various frontier models and find that most models are fairly, but not perfectly, monitorable.<n>We show we can improve monitorability by asking models follow-up questions and giving their follow-up CoT to the monitor.
  arXiv  Detail & Related papers  (2025-12-20T10:46:04Z)
• Practical challenges of control monitoring in frontier AI deployments [15.281070904065613]
  Control monitors could play an important role in overseeing highly capable AI agents that we do not fully trust.<n>Previous work has explored control monitoring in simplified settings, but scaling monitoring to real-world deployments introduces additional dynamics.<n>In this paper, we analyse design choices to address these challenges, focusing on three forms of monitoring with different latency-safety trade-offs.
  arXiv  Detail & Related papers  (2025-12-15T15:54:36Z)
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition [52.232968183793986]
  General Policy Composition (GPC) is a training-free method that enhances performance by combining the distributional scores of multiple pre-trained policies.<n>GPC consistently improves performance and adaptability across a diverse set of tasks.
  arXiv  Detail & Related papers  (2025-10-01T16:05:53Z)
• Beyond Linear Probes: Dynamic Safety Monitoring for Language Models [67.15793594651609]
  Traditional safety monitors require the same amount of compute for every query.<n>We introduce Truncated Polynomials (TPCs), a natural extension of linear probes for dynamic activation monitoring.<n>Our key insight is that TPCs can be trained and evaluated progressively, term-by-term.
  arXiv  Detail & Related papers  (2025-09-30T13:32:59Z)
• RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation [67.38036090822982]
  We propose RoboView-Bias, the first benchmark specifically designed to quantify visual bias in robotic manipulation.<n>We create 2,127 task instances that enable robust measurement of biases induced by individual visual factors and their interactions.<n>Our results highlight that systematic analysis of visual bias is a prerequisite for developing safe and reliable general-purpose embodied agents.
  arXiv  Detail & Related papers  (2025-09-26T13:53:25Z)
• Combining Cost-Constrained Runtime Monitors for AI Safety [0.25655761752240497]
  We study how to efficiently combine multiple runtime monitors into a single monitoring protocol.<n>Our framework provides a principled methodology for combining existing monitors to detect undesirable behavior.
  arXiv  Detail & Related papers  (2025-07-19T04:28:40Z)
• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring [3.6284577335311563]
  Chain-of-Thought (CoT) monitoring improves detection by up to 27 percentage points in scenarios where action-only monitoring fails to reliably identify sabotage.<n>CoT traces can also contain misleading rationalizations that deceive the monitor, reducing performance in more obvious sabotage cases.<n>This hybrid monitor consistently outperforms both CoT and action-only monitors across all tested models and tasks, with detection rates over four times higher than action-only monitoring for subtle deception scenarios.
  arXiv  Detail & Related papers  (2025-05-29T15:47:36Z)
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation [56.102976602468615]
  We show that we can monitor a frontier reasoning model, such as OpenAI o3-mini, for reward hacking in agentic coding environments.<n>We find that with too much optimization, agents learn obfuscated reward hacking, hiding their intent within the chain-of-thought.
  arXiv  Detail & Related papers  (2025-03-14T23:50:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.