Cover Image

Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Koran, Eugene, Yun, Yejun, Tetef, Samantha, Arnav, Benjamin, Bernabeu-Pérez, Pablo
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
by: Arnav, Benjamin, et al.
Published: (2025)

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
by: Feuer, Benjamin, et al.
Published: (2024)

The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
by: Radev, Nikolay, et al.
Published: (2026)

Collaborative Comic Generation: Integrating Visual Narrative Theories with AI Models for Enhanced Creativity
by: Chen, Yi-Chun, et al.
Published: (2024)

Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers
by: Samuel, Saron, et al.
Published: (2026)

Monitoring Monitorability
by: Guan, Melody Y., et al.
Published: (2025)

Automated Real-time Assessment of Intracranial Hemorrhage Detection AI Using an Ensembled Monitoring Model (EMM)
by: Fang, Zhongnan, et al.
Published: (2025)

Present and Future Generalization of Synthetic Image Detectors
by: Bernabeu-Perez, Pablo, et al.
Published: (2024)

Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI
by: Aijaz, Aisha, et al.
Published: (2026)

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models
by: Zhang, Michael S., et al.
Published: (2025)

A Unified Theory of Diversity in Ensemble Learning
by: Wood, Danny, et al.
Published: (2023)

Diverse Projection Ensembles for Distributional Reinforcement Learning
by: Zanger, Moritz A., et al.
Published: (2023)

SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras
by: Chen, Tiejin, et al.
Published: (2024)

Computational Safety for Generative AI: A Signal Processing Perspective
by: Chen, Pin-Yu
Published: (2025)

Factor(U,T): Controlling Untrusted AI by Monitoring their Plans
by: Lip, Edward Lue Chee, et al.
Published: (2025)

GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation
by: Dhole, Kaustubh, et al.
Published: (2024)

AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
by: Barke, Shraddha, et al.
Published: (2026)

Less is More: Undertraining Experts Improves Model Upcycling
by: Horoi, Stefan, et al.
Published: (2025)

AI Needs Physics More Than Physics Needs AI
by: Coveney, Peter, et al.
Published: (2025)

Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks
by: Aravind, Aditi, et al.
Published: (2026)

INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning
by: Romero, Pablo, et al.
Published: (2024)

Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection
by: Syed, Qutub, et al.
Published: (2024)

AI Should Be More Human, Not More Complex
by: Esposito, Carlo
Published: (2025)

VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration
by: Jung, Jaeyoon, et al.
Published: (2026)

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
by: Yun, Heecheol, et al.
Published: (2025)

Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understanding
by: Lin, Zhiming
Published: (2025)

GuideLight: "Industrial Solution" Guidance for More Practical Traffic Signal Control Agents
by: Jiang, Haoyuan, et al.
Published: (2024)

Diverse Controllable Diffusion Policy with Signal Temporal Logic
by: Meng, Yue, et al.
Published: (2025)

Stable LLM Ensemble: Interaction between Example Representativeness and Diversity
by: Niimi, Junichiro
Published: (2025)

AI in Support of Diversity and Inclusion
by: Güven, Çiçek, et al.
Published: (2025)

Transforming Computational Lithography with AC and AI -- Faster, More Accurate, and Energy-efficient
by: Mukhopadhyay, Saumyadip, et al.
Published: (2026)

Does More Inference-Time Compute Really Help Robustness?
by: Wu, Tong, et al.
Published: (2025)

Training a high-performance retinal foundation model with half-the-data and 400 times less compute
by: Engelmann, Justin, et al.
Published: (2024)

B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency
by: Puniani, Cherish, et al.
Published: (2026)

Driving Intelligent IoT Monitoring and Control through Cloud Computing and Machine Learning
by: Li, Hanzhe, et al.
Published: (2024)

A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
by: Niimi, Junichiro
Published: (2025)

Learning Causally Invariant Reward Functions from Diverse Demonstrations
by: Ovinnikov, Ivan, et al.
Published: (2024)

Hodoscope: Unsupervised Monitoring for AI Misbehaviors
by: Zhong, Ziqian, et al.
Published: (2026)

RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI
by: Kim, Eugene, et al.
Published: (2025)

Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
by: Sadowski, Michal, et al.
Published: (2025)