arXiv AI
Aug 13
Agent Safety Should Be a Runtime Contract
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
AI Safety Considerations for Agents With Limited Time to Act
Related stories
arXiv Machine Learning
Jun 25
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
arXiv:2606. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.
arXiv AI
Jun 30
Agentic Safety is an Epistemic Property, Not a Behavioral One
arXiv:2606. 28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming.
arXiv AI
Jul 1
Containment Verification: AI Safety Guarantees Independent of Alignment
arXiv:2605. 09045v2 Announce Type: replace Abstract: Agentic frameworks are the software layer through which AI agents act in the world.
arXiv AI
Sep 15
Math for AI safety: an invitation for mathematicians
The article "Math for AI safety: an invitation for mathematicians" calls for new mathematical tools to ensure AI remains understandable, controllable, and cooperative. It outlines specific mathematical fields—logic, game theory, probability, algebra, representation theory, analysis, and geometry—each paired with an open problem tailored for mathematicians without AI safety background. The piece invites researchers to contribute to designing AI that is legible, steerable, and aligned with human values.
arXiv AI
Jun 16
Resilient Consensus in Agentic AI
arXiv:2606. 15024v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions.
arXiv AI
Aug 6
SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
arXiv:2608. 04289v1 Announce Type: new Abstract: Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects.
arXiv AI
Sep 15
Safety Signals to Verify NetOps Agents with Action-Level Granularity
arXiv:2609.14422v1 Announce Type: new Abstract: Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. Whi...
OpenAI Blog
Apr 5, 2023
Our approach to AI safety
Ensuring that AI systems are built, deployed, and used safely is critical to our mission.
arXiv AI
Aug 28
Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents
The paper demonstrates that safety mechanisms for autonomous large language model agents fail to compose across iterative loops, as trajectory‑scoped monitors cannot detect attacks whose evidence is spread over multiple iterations. It introduces LoopHarness, a system that maintains a persistent, non‑decaying safety state across loops, bounding unauthorized actions with a constant that does not grow with the number of iterations. The authors provide a comprehensive evaluation protocol, including attacks that require cross‑iteration evidence, module ablations, and adaptive white‑box red‑team testing.
arXiv Machine Learning
Oct 8
RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment
arXiv:2610.09294v1 Announce Type: cross Abstract: Rapid progress in AI agents has brought growing attention to agent safety, with extensive evaluation focused on digital environments. As agents move...
arXiv AI
Aug 18
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.