AI agents today are capable of self-directed collaboration, delegation, and decision-making. They operate not only on user ...

To demonstrate the dangers in the use of AI agents for action rather than advice, a real world example of AI agents used in ...

Recent research demonstrates that such attacks could cause potentially catastrophic outcomes if such agents are given control ...

Professor Manling Li and CS PhD student Zihan Wang led a multi-institution team in the development of an AI framework ...

However, if we're going to launch agents, we should also launch an evaluation framework ... Two concrete examples: A user builds a long-running agent that makes an uncapped number of calls to an LLM ...

Without robust security measures in place, AI infrastructure remains vulnerable to threats such as data leakage or fraud, ...

Through the LangGraph Platform, organizations can deploy agents with one-click deployment, horizontal scaling to handle “bursty, long-running traffic." ...

A new paper from Microsoft Research and Salesforce finds that even the most capable Large Language Models (LLMs) fall apart ...

In this exclusive episode of DEMO, Keith Shaw speaks with Taylor Pechacek, Head of Product for API Collaboration Core at ...