AI Agent Safety

Ask about this topic

Momentum

22 papers in the last four weeks, up 144% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 207

All topics
CardsList

  1. Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI Execution

    May 11, 2026Kai Pan, Rong HouLLM Agent OrchestrationAI Agent Safety

    A2A Lab

  2. The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents

    May 10, 2026Baoyuan Wu, Qingshan Liu, Adel Bibi +2Agent Failure AnalysisAI Agent Security

    Chinese University of Hong Kong, Shenzhen, China · Nanjing University of Posts and Telecommunications, China · University of Oxford, UK +2

  3. A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web

    May 10, 2026Shusaku Egami, Masahiro HamasakiAI Agent SafetyLLM Agent Reliability

    National Institute of Advanced Industrial Sciencen and Technology (AIST) · Koto, Tokyo, Japan

  4. Containment Verification: AI Safety Guarantees Independent of Alignment

    May 9, 2026Royce Moon, Lav R. VarshneyAI Agent SafetyFormal Verification

    Enclave Intelligence · AI Innovation Institute, Stony Brook University

  5. Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI

    May 8, 2026Xuanqiang Angelo Huang, Charlie Tharas, Samuele Marro +4Mechanism DesignAI Agent Safety

    ETH Zürich · University of Oxford · Institute for Decentralized AI +5

  6. Playing games with knowledge: AI-Induced delusions need game theoretic interventions

    May 8, 2026Will Beaumaster, Paul SchraterLLM SycophancyMechanism Design

    University of Minnesota

  7. Why Does Agentic Safety Fail to Generalize Across Tasks?

    May 7, 2026Yonatan Slutzky, Yotam Alexander, Tomer Slor +2AI Agent SafetyLLM Agent Safety

    Tel Aviv University

  8. Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

    May 7, 2026Jonas Wiedermann-Möller, Leonard Dung, Maksym AndriushchenkoAI Agent EvaluationAI Agent Safety

    Universität Bielefeld · Ruhr-Universität Bochum · ELLIS Institute Tübingen +2

  9. Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

    May 7, 2026Xinquan Chen, Zhenyun Yin, Shan He +38Agentic RLAI Agent Safety

  10. Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges

    May 7, 2026Shihao Weng, Yang Feng, Xiaofei XieLLM-as-a-JudgeAI Agent Safety

    Nanjing University Nanjing, China · Singapore Management University Singapore

  11. TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains

    May 5, 2026Serhii ZabolotniiAI Agent SafetyAI Agent Governance

    Cherkasy State Business College, Cherkasy 18028, Ukraine · State Scientific Research Institute of Armament and Military Equipment Testing and Certification, Cherkasy, Ukraine · healthPrecision, New York, NY, USA

  12. Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios

    May 5, 2026Zuoyu Zhang, Yancheng ZhuAI Agent SafetyAI Agent Safety Benchmarks

    Shenzhen University, Shenzhen, China.

  13. An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance

    May 4, 2026Gelei Xu, Ningzhi Tang, Xueyang Li +4HealthcareAI Agent Safety

    University of Notre Dame · Emory University

  14. Executor-Side Progressive Risk-Gated Actuation for Agentic AI in Wireless Supervisory Control

    May 4, 2026Zhenyu Liu, Yi Ma, Rahim TafazolliSafety-Critical ControlAI Agent Safety

    6GIC, Institute for Communication Systems, University of Surrey, Guildford, United Kingdom, GU2 7XH

  15. MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

    May 2, 2026Jiyao Wang, Yunbiao Wang, Yubo Jiao +6AI AlignmentAI Agent Safety

    Department of Civil Engineering, McGill University, Montreal H3A 0G4, Quebec, Canada · Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, Guangdong, China · Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg L-4365, Luxembourg

  16. Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment

    May 1, 2026Tanav Singh Bajaj, Nikhil Singh, Karan Anand +1Opinion DynamicsAI Agent Safety

    Department of Computer Science, University of British Columbia, Vancouver, Canada · Department of Artificial Intelligence, IIT Hyderabad, Hyderabad, India · Amazon, Delhi, India.

  17. AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems

    May 1, 2026Ivan LetteriMulti-Agent OrchestrationAI Agent Safety

    Department of Information Engineering, Computer Science, and Mathematics, Center of Excellence for Research DEWS, University of L’Aquila, Via Vetoio, Coppito, 67100 L’Aquila, Italy

  18. Causal Foundations of Collective Agency

    Apr 30, 2026Frederik Hytting Jørgensen, Sebastian Weichwald, Lewis HammondAI Agent SafetyCausal Abstraction

    Copenhagen Causality Lab and Pioneer Centre for AI, University of Copenhagen, Denmark · Cooperative AI Foundation, United Kingdom

  19. Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems

    Apr 30, 2026Yuan SunAI Agent SafetyMulti-Agent Systems

    Jilin University

  20. Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure

    Apr 29, 2026Diego F. Cuadros, Abdoul-Aziz MaigaAgent Failure AnalysisAI Agent Security

    Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, USA · Center for Humanities and Technology (CHaT), University of Cincinnati, Cincinnati, OH, USA · Norwegian University of Science and Technology, Trondheim, Norway

  21. Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents

    Apr 27, 2026Maximiliano Armesto, Christophe KolbAI Agent EvaluationAI Agent Safety

    Taller Technologies

  22. Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents

    Apr 27, 2026German Marin, Jatin ChaudharyAI Agent SafetyAI Agent Monitoring

    Department of Computing, University of Turku, Turku, Finland

  23. Evaluating whether AI models would sabotage AI safety research

    Apr 27, 2026Robert Kirk, Alexandra Souly, Kai Fronsdal +2Language Model Safety EvaluationLLM Auditing

    UK AI Security Institute · UK AISI Research Affiliate

  24. OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents

    Apr 27, 2026Zheng Wu, Yi Hua, Zhaoyuan Huang +8Computer-Use AgentsAI Agent Evaluation

    School of Computer Science, Shanghai Jiao Tong University

  25. Benchmarking Web Agent Safety under E-commerce Deceptive Interfaces

    Apr 26, 2026Zijing Shi, Meng Fang, Ling ChenWeb Agent BenchmarksAI Agent Safety

    AAII, University of Technology Sydney, NSW, Australia · University of Liverpool, Liverpool, UK

  26. Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

    Apr 26, 2026Qi Li, Bo Yin, Weiqi Huang +6AI Agent SafetyAdversarial Attacks on VLA Models

    National University of Singapore · Peking University · Monash University

  27. Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture

    Apr 26, 2026Rong XiangAI Agent SecurityAI Agent Safety

  28. Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems

    Apr 24, 2026Marcelo Fernandez - TraslaIAAI Agent SecurityAI Agent Safety

    TraslaIA

  29. Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems

    Apr 24, 2026Jun He, Deying YuLLM Agent SecurityAI Agent Safety

  30. Interval POMDP Shielding for Imperfect-Perception Agents

    Apr 22, 2026William Scarbro, Ravi MangalSafety-Critical ControlAI Agent Safety

    Department of Computer Science Colorado State University Fort Collins, USA