LLM Agent Safety

LLM: Large Language Model

Ask about this topic

Momentum

24 papers in the last four weeks, up 50% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 193

All topics
CardsList

  1. What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents

    Jul 24, 2026Shawn RayRuntime Enforcement for AI AgentsRuntime Assurance

    Carnegie Mellon University

  2. DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents

    Jul 24, 2026Junming Chen, Junyang Jiang, Xu Chen +2Benchmark DesignAI Agent Benchmarks

    University of Electronic Science and Technology of China Chengdu, China

  3. Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation

    Jul 23, 2026Linjun LiMulti-Agent LLM SystemsLLM Safety

    Department of Mathematics, University of Pennsylvania, Philadelphia, PA.

  4. Auditing Provenance Sensitivity in LLM Agent Action Selection

    Jul 23, 2026Junchi LiaoAI Agent AuditingLLM Auditing

  5. JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety

    Jul 22, 2026Yuan Xiong, Linji Hao, Shizhu He +2AI Agent SafetyLLM Agent Safety

    The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Peking University, Beijing, China +2

  6. Agents in the Wild: Where Research Meets Deployment

    Jul 21, 2026Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz +3AI Agent ReliabilityMulti-Agent LLM Systems

    Georgetown University · Washington, D.C., USA · Salesforce +7

  7. They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface

    Jul 21, 2026Yohann SidotLLM Agent SecurityIndirect Prompt Injection

    Senthex Research

  8. Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

    Jul 21, 2026Aarushi SinghAI Agent ReliabilityLLM Agent Evaluation

    Independent Researcher India

  9. ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

    Jul 20, 2026Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria +2LLM Agent SecurityPrompt Injection Attacks on AI Agents

    University of Central Florida · 2North South University · 3Ahsanullah University of Science and Technology +1

  10. Operational Hallucination and Safety Drift in AI Agents

    Jul 20, 2026Shasha Yu, Fiona Carroll, Barry L. BentleyLLM Agent EvaluationAI Agent Safety

    Cardiff School of Technologies, Cardiff Metropolitan University Cardiff, UK · Harvard Medical School, Harvard University Boston, USA

  11. ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs

    Jul 15, 2026Aryan Keluskar, Amrita Bhattacharjee, Huan LiuLLM AlignmentAI Agent Safety Benchmarks

    School of Computing & AI, Arizona State University, Tempe, AZ, USA.

  12. SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing

    Jul 15, 2026Tianyu Chen, Chujia Hu, Wenjie WangLanguage Model Safety EvaluationLLM Guardrails

    ShanghaiTech University, Shanghai, China

  13. Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

    Jul 14, 2026Huihao Jing, Wenbin Hu, Shaojin Chen +10LLM Agent SecurityLLM Agent Safety

    HKUST · NYU · SWUPL

  14. Self-Aware Recursively Self-Improving Agents for Personal Singularity: A Goal-, Scope-, Tool-, and Benchmark-Driven Multi-Agent Architecture

    Jul 14, 2026Chengshuai YangMulti-Agent LLM SystemsLLM Agent Self-Improvement

    NextGen PlatformAI C Corp.

  15. Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory

    Jul 13, 2026Tengjiao LiuMulti-Agent LLM SystemsLLM Agent Memory

    Founder & Researcher, psi.run

  16. LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans

    Jul 12, 2026Yuma Ichikawa, Yamato Arai, Kosaku Kimura +2Multi-Agent LLM SystemsHuman-in-the-Loop AI

    1Fujitsu Limited · 2RIKEN Center for AIP · 4Tokai University

  17. Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF

    Jul 12, 2026Chinmayi DixitSynthetic Data Generation for Language ModelsLLM Agent Safety

    ERA Fellowship

  18. Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering

    Jul 10, 2026Lucas PintoTool-Using AgentsLLM Agent Safety

    Independent Researcher

  19. The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents

    Jul 8, 2026Xing Zhang, Yanwei Cui, Guanghui Wang +4LLM-as-a-JudgeLLM Agent Safety

    1AWS Generative AI Innovation Center · 2HSBC Holdings Plc., HSBC Technology Center, China

  20. Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety

    Jul 8, 2026Lifei Liu, Haoran Yu, Xiaochong Jiang +3Multi-Agent LLM SystemsLLM Safety Evaluation

    Independent Researcher Seattle, WA, USA · Carnegie Mellon University Pittsburgh, PA, USA · Georgia Institute of Technology Atlanta, GA, USA

  21. Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents

    Jul 7, 2026Wael Albayaydh, Rui Zhao, Ivan FlechaisAI Agent ReliabilityLLM Agent Evaluation

    University of Oxford

  22. Toward Trustworthy Large Language Model Agents in Healthcare

    Jul 6, 2026Hadi Hasan, Safaa Salman, Adam Tai Abou Dargham +2HealthcareLLM Agent Safety

    Department of Electrical and Computer Engineering / American University of Beirut / Beirut, Lebanon

  23. Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses

    Jul 6, 2026Neeraj Karamchandani, Piyush Nagasubramaniam, Sencun Zhu +1LLM Agent MemoryAgent Memory Poisoning

    The Pennsylvania State University, University Park, PA, USA

  24. Agentic-V2X: Small Language Model Agents for Deadline-Aware V2X Scheduling in 5G/6G Networks

    Jul 5, 2026Gerasimos Papanikolaou-Ntais, Alexandros Kaloxylos, Athanasios KanavosLanguage Model-Based ControlSmall Language Models

    Department of Informatics, University of Piraeus, 185 34 Piraeus, Greece · Department of Informatics and Telecommunications, University of Peloponnese, 221 31 Tripoli, Greece

  25. Biological Motifs for Agentic Control

    Jul 5, 2026Bogdan BanuMulti-Agent LLM SystemsLLM Agent Security

  26. Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents

    Jul 4, 2026Abhishek Kumar, Carsten MapleLanguage Model Safety EvaluationAI Coding Agents

    The Alan Turing Institute, London, United Kingdom

  27. DualView: Preventing Indirect Prompt Injection in Personal AI Agents

    Jul 4, 2026Juhee Kim, Woohyuk Choi, Taehyun Kang +2LLM Agent SecurityIndirect Prompt Injection

    Seoul National University

  28. SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces

    Jul 2, 2026Jinwei Hu, Yi Dong, Youcheng Sun +1LLM AgentsAgent Skill Security Auditing

    School of Computer Science and Informatics, University of Liverpool, Liverpool, United Kingdom · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

  29. Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

    Jul 2, 2026Yunhao Feng, Ruixiao Lin, Ming Wen +12AI Agent SafetyAI Agent Safety Benchmarks

    AntGroup · Hunan Institute of Advanced Technology · Zhejiang University +3

  30. Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows

    Jun 30, 2026Edward Y. Chang, Longling GengAgentic WorkflowsAI Agent Safety

    Stanford University