arXiv:2607. 05163v1 Announce Type: cross Abstract: AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2605. 16281v2 Announce Type: replace-cross Abstract: Post-deployment accountability has become central to AI governance, yet little empirical evidence shows whether monitoring, incident reporting, and impact assessment obligations are visible when AI systems fail.
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. 08376v1 Announce Type: cross Abstract: As artificial intelligence (AI) systems are increasingly deployed across socially consequential domains, reports of AI-related harms and failures have grown in frequency and diversity.
arXiv:2606. 31567v1 Announce Type: cross Abstract: Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety.
arXiv:2607. 25648v1 Announce Type: cross Abstract: Public services face growing pressure to adopt artificial intelligence (AI) to close the gap between rising demand and falling resources.
AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare public failures with agent-security evaluations. We...