Overview

AI agent safety asks how to keep systems that plan over multiple steps and use tools, memory, or other agents within authorized and harmless bounds. Researchers test computer-use, coding, web, and embodied agents with prompt-injection, misuse, and long-horizon trajectory benchmarks, measuring executed effects as well as final answers. Approaches include red-teaming and monitoring, safety fine-tuning and refusal training, and runtime controls such as least-privilege access, pre-execution policy gates, sandboxing, human approval, and formal verification. A central challenge is that safety can fail through ambiguous goals, changing context, tool or agent interactions, and pressure over time, while stronger restrictions can block legitimate tasks and assurances may not transfer to deployment.

Latest papers

CardsList

353 papers28 papers in the last four weeks, down 49% on the four weeks before. 0.2% of all new papers.

  1. Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

    Mar 5, 2026Yida Lu, Jianwei Fang, Xuyang Shao +7LLM SafetyAI Agent Safety

  2. Asymmetric Goal Drift in Coding Agents Under Value Conflict

    Mar 3, 2026Magnus Saebo, Spencer Gibson, Tyler Crosse +3AI Coding AgentsAI Agent Safety

  3. Evaluating and Understanding Scheming Propensity in LLM Agents

    Mar 2, 2026Mia Hopman, Jannes Elstner, Maria Avramidou +2AI Agent SafetyLLM Agents

  4. Tracking Capabilities for Safer Agents

    Mar 1, 2026Martin Odersky, Yaoyu Zhao, Yichen Xu +2AI Agent SafetyTool Access Control for LLM Agents

  5. The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety

    Feb 28, 2026Elias Malomgré, Pieter SimoensAI Agent SafetyAI Agent Monitoring

  6. Training Agents to Self-Report Misbehavior

    Feb 25, 2026Bruce W. Lee, Chen Yueh-Han, Tomek KorbakAI Agent SafetyLLM Agent Training

  7. The Ghost in the Grammar: Methodological Anthropomorphism in AI Safety Evaluations

    Feb 24, 2026Mariana Lins CostaAnthropomorphism in AIAI Safety

  8. Agents of Chaos

    Feb 23, 2026Natalie Shapira, Chris Wendler, Avery Yen +35AI Agent SecurityLLM Agent Security

  9. The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems

    Feb 19, 2026Leon Staufer, Kevin Feng, Kevin Wei +6AI Agent AuditingAI Agent Safety

  10. Towards a Science of AI Agent Reliability

    Feb 18, 2026Stephan Rabanser, Sayash Kapoor, Peter Kirgis +3AI Agent ReliabilityAI Agent Evaluation

  11. Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight

    Feb 16, 2026Kirandeep Kaur, Xingda Lyu, Chirag ShahProactive AssistanceHuman-Centered AI

  12. A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)

    Feb 16, 2026Tianyu Chen, Dongrui Liu, Xia Hu +2AI Agent SecurityAI Agent Safety

  13. When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents

    Feb 9, 2026Yuting Ning, Jaylen Jones, Zhehao Zhang +5LLM Self-CorrectionComputer-Use Agents

  14. Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique

    Jan 21, 2026Joyjit Roy, Samaresh Kumar SinghLLM Self-CorrectionAI Agent Safety

  15. When Assisting One Disempowers Another

    Nov 6, 2025Claire Yang, Claire Jie Zhang, Maya Cakmak +1AI Agent SafetyHuman-Centered AI

  16. Measuring Harmfulness of Computer-Using Agents

    Jul 31, 2025Aaron Xuxiang Tian, Ruofan Zhang, Janet Tang +3LLM Agent SafetyComputer-Use Agent Benchmarks

  17. Towards Shutdownable Agents via Stochastic Choice

    Jun 30, 2024Elliott Thornley, Alexander Roman, Christos Ziakas +2CorrigibilityAI Agent Safety