AI Control

Ask about this topic

Overview

The field studies both how AI controls robots and other physical systems and how people can keep autonomous AI agents within defined limits. For embodied control, common approaches include vision-language-action policies, world-action models, model-based planning, and closed-loop skill execution, evaluated in suites such as LIBERO and Meta-World as well as on real robots. For agent oversight, researchers use runtime permission gates, shutdown and override mechanisms, and monitors for tool misuse or sabotage, tested in software environments such as BashArena and LinuxArena. A central tension is that agents need to adapt and act over long horizons, while safeguards can miss strategic or unfamiliar failures, making realistic evaluation and persistent intervention important open challenges.

Latest papers

CardsList

66 papers5 papers in the last four weeks, up 25% on the four weeks before. 0.0% of all new papers.

  1. Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors

    Oct 22, 2026Juan-Pablo Rivera, Ari Spiesberger, Juan J Vazquez +6AI ControlLLM Safety Monitoring

    Meridian Cambridge · Arb Research · Redwood Research +3

  2. RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?

    Oct 20, 2026Kaiwen Zhou, Udari Madhushani SehwagRecursive Self-ImprovementAI Control

    Preparedness and Policy, Scale AI

  3. An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers

    Sep 29, 2026Hadiza Umar Yusuf, Khouloud GaaloulCyber-Physical SystemsSafety-Critical Control

    University of Michigan-Dearborn Dearborn, USA.

  4. A Competing-Hazards Systematization of Loss of Control in Autonomous Agents

    Sep 29, 2026Mohamed Aly BoukeAgent Failure AnalysisAI Agent Auditing

    Centre for Intelligent Cloud Computing, CoE for Advanced Cloud, Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia

  5. What if automating AI R&D triggers an intelligence explosion?

    Sep 28, 2026Alan Chan, Christoph Winter, Andrew Barto +19AI ControlAI Governance

    GovAI · CASP, University of Cambridge, Institute for Law & AI · University of Massachusetts Amherst +14

  6. Functional Architecture of European Electricity Trading Markets: Requirements for AI Supported Trading Systems under Regulatory Constraints

    Sep 24, 2026Walter Kurz, Wojtek StrickerAI ControlRuntime Enforcement for AI Agents

    Swissi Institute for AI

  7. Reliability Theory for AI Control

    Sep 22, 2026Grant MolnarAI Agent ReliabilityAI Control

    Google DeepMind

  8. AI Persuasion as a Threat to Human Control

    Sep 13, 2026Joshua Levy, Mick Yang, Kellin PelrineAI ControlAI Governance

  9. Training-Free Task Vectors for LLM Behavioral Control

    Sep 8, 2026Gabriel J. Perin, Lucas Boscaini, André Araujo +1Task VectorsAI Control

    University of São Paulo · Google · Google DeepMind

  10. AI Control Scientist: LLM-driven Agentic System for Automated Control Design

    Aug 27, 2026Haiteng Wang, Weihao Li, Jing Zhang +1AI ControlLLM Agents

  11. Real-time virtual circuits for plasma shape control via neural network emulators: integration and testing in the MAST-U PCS

    Aug 26, 2026Matthew J. Marshall, Edward Jones, Graham J. McArdle +10AI ControlFeedback Control

    Hartree Centre, STFC, Daresbury Laboratory, Daresbury, WA4 4AD, United Kingdom · UKAEA, Culham Campus, Abingdon, OX14 3DB, United Kingdom

  12. Software Engineering for AI-driven Building Operation

    Aug 17, 2026Philipp Zech, Sascha Hammes, Johannes Weninger +2Software EngineeringAI Control

    University of Innsbruck, Tyrol, Austria · Bartenbach - The Lighting Innovators, Wattens, Austria · University of Applied Sciences Burgenland, Austria

  13. Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous

    Aug 14, 2026Adam M. ObermanAI Agent SafetyAI Control

    McGill University; Mila, Quebec AI Institute; LawZero

  14. ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

    Jul 21, 2026Lena Libon, Ben Rank, Jehyeok Yeon +5AI Agent MonitoringAI Control

    ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center · ETH Zurich · University of Amsterdam

  15. Hardware Mechanisms to Dynamically Throttle AI Performance

    Jul 20, 2026Haiyue Ma, Lauren Malek, Joseph Forzani +1AI ControlAI Safety

    Princeton University Electrical and Computer Engineering Princeton, NJ, USA

  16. Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors

    Jul 8, 2026Oliver Makins, Orazio Angelini, Zohreh Shams +1Multi-Agent ControlAI Agent Security

    UK AI Security Institute · MATS Research

  17. Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages

    Jul 6, 2026Lucas PintoBackdoor DetectionAI Agent Monitoring

    Independent Researcher

  18. TypeGo: An OS Runtime for Embodied Agents

    Jul 6, 2026Guojun Chen, Alex Schott, Lin ZhongLanguage Model-Based ControlLarge Language Model-Based Robot Planning

    Yale University

  19. InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

    Jul 6, 2026Haoxiang Ma, Junhao Cai, Xiaoxu Xu +26Generalization in Robotic ManipulationVisuomotor Policy Learning

    Physical Intelligence Team, Shanghai AI Laboratory

  20. Distributed Attacks in Persistent-State AI Control

    Jul 2, 2026Josh Hills, Ida Caspary, Asa Cooper SticklandAI Agent SecurityAI Agent Security Benchmarks

    1Constellation Astra Fellowship · 2Imperial College London · 3UK AI Security Institute

  21. ASPIRE: Agentic /Skills Discovery for Robotics

    Jun 30, 2026Runyu Lu, Yubo Wu, Ethan Kou +13Robot Policy LearningLong-Horizon Robotic Manipulation

    NVIDIA · UMich · UIUC +2

  22. Sequential Planning via Anchored Robotic Keypoints

    Jun 29, 2026Bryce Grant, Aryeh Rothenberg, Logan Senning +3Language-Conditioned Robot ManipulationGeneralization in Robotic Manipulation

    Department of Electrical, Computer, and Systems Engineering, Case Western Reserve University, United States · Department of Mechanical and Aerospace Engineering, Case Western Reserve University, United States

  23. AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes

    Jun 29, 2026Anjali Rao, Nikhil Kamalkumar AdvaniLanguage Model-Based ControlLarge Language Model-Guided Optimization

    Independent Researcher Mountain View, California

  24. GPC: Large-Scale Generative Pretraining for Transferable Motor Control

    Jun 28, 2026Yi Shi, Yifeng Jiang, Chen Tessler +1RL ControlHuman Motion Generation

    Simon Fraser University, Canada and NVIDIA, USA · NVIDIA, USA · Simon Fraser University, Canada and NVIDIA, Canada

  25. Reflective VLA: In-Context Action Consequences Make VLAs Generalize

    Jun 23, 2026Qing Lian, Kent Yu, Lei ZhangICL for RoboticsGeneralization in Robotic Manipulation

    Futian Laboratory · International Digital Economy Academy (IDEA) · Visincept

  26. LaGO: Latent Action Guidance for Online Reinforcement Learning

    Jun 23, 2026Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong WuLatent Action LearningLLM-Guided RL

    Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, USA · Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan.

  27. ASCII Art Turns LLMs into VLA Controllers

    Jun 19, 2026Yitao Jiang, Roy Xing, Luyang Zhao +3Language Model-Based ControlAI Control

    Dept. of Computer Science, Dartmouth College, Hanover, NH, USA. · Dept. of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA. · Dept. of Mechanical and Aerospace Engineering, University of Houston, Houston, TX, USA.

  28. Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection

    Jun 18, 2026Trong-Bao Ho, Quang-Tan Nguyen, Thien-Loc Ha +7Robotic ControlRobot Policy Learning

    VinRobotics · VinUniversity · DFKI +2

  29. ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift

    Jun 16, 2026Jeffery Opoku, David BanaheneAI Agent ReliabilityDistribution Shift

    The University of Texas Rio Grande Valley, Edinburg, TX, USA · Florida International University, Miami, FL, USA

  30. Self-CTRL: Self-Consistency Training with Reinforcement Learning

    Jun 16, 2026Itamar Pres, Laura Ruis, Melat Ghebreselassie +2Self-Consistency in Language ModelsFaithfulness of Language Model Explanations

    MIT CSAIL