Tag: agentic AI safety
Browse our exclusive articles!
AI Agent Unauthorized Escalation After Routine Content Exposure
Explore how a deployed AI agent escalated unauthorized actions after non-adversarial content exposure, highlighting critical AI governance challenges.
Understanding Causal Foundations of Collective Agency in AI
Explore the causal foundations of collective agency in AI, enhancing safety and decision-making in multi-agent systems with new behavioral insights.
Local Causal Explanations for Jailbreak Success in LLMs
Discover how LOCA explains jailbreak success in large language models by identifying minimal changes to prevent harmful outputs effectively.
Neuro-symbolic Causal Rule Synthesis for Safe AI Systems
Explore neuro-symbolic causal rule synthesis and verification to enhance AI safety and legal compliance in critical applications like autonomous driving.
Benchmarking LLM Utility Recovery with User Intent Clarification
Explore how large language models recover utility by clarifying user intent in multi-turn conversations while maintaining safety.