Securing internal systems with an AI Control Roadmap, combining traditional safeguards and real-time monitoring.
arXiv:2606. 14816v1 Announce Type: cross Abstract: This paper presents a structured analysis of security challenges in long-horizon agentic AI systems.
Ensuring that AI systems are built, deployed, and used safely is critical to our mission.
arXiv:2607. 07612v1 Announce Type: cross Abstract: Artificial intelligence is rapidly evolving from generative systems to agentic AI capable of autonomously planning and executing tasks.
The paper discusses the need to adapt incident reporting frameworks for AI agents, which are rapidly deployed and face unique security challenges. By comparing AI systems and agents and consulting 23 experts, the authors identify key reporting elements such as agent memory, autonomy levels, and tool usage. They also highlight open research questions, potential reporting weaknesses like data leakage, and outline privacy requirements for secure AI agent deployment.
arXiv:2606. 11998v1 Announce Type: new Abstract: Trusted monitoring is a cornerstone of AI control.
arXiv:2608. 14565v1 Announce Type: new Abstract: AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of generative AI's societal impacts (including unemployment risk and labor market disruption).
We’ve written a policy research paper identifying four strategies that can be used today to improve the likelihood of long-term industry cooperation on safety norms in AI: communicating risks and benefits, technical collaboration, increased transparency, and incentivizing standards. Our analysis shows that industry cooperation on safety will be instrumental in ensuring that AI systems are safe and beneficial, but competitive pressures could lead to a collective action problem, potentially causing AI companies to under-invest in safety.
The article proposes a structured framework of behavioral indicators that could signal a progression toward potentially catastrophic threats from AI systems. Drawing on established methods from cybersecurity and national security, it defines clear metrics, indicators, and thresholds across multiple dimensions of AI capability and behavior. The framework is intended to enable researchers and policymakers to implement evidence‑based monitoring protocols for rogue AI progression.
arXiv:2604. 15579v2 Announce Type: replace-cross Abstract: There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents.
arXiv:2607. 10878v1 Announce Type: new Abstract: AI agents are evolving from answer engines into persistent teams that use tools, delegate work, learn from experience, and modify the artifacts that shape their future behavior.
arXiv:2608.22930v1 Announce Type: new Abstract: Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to "conventional" AI assisted coding, which in turn w...