Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended iterations. The agent safeguards in wide use, however, are defined over a single trajectory, and their safety state is re-initialized when the next trajectory begins. We show that this is a failure of composition rather than an implementation detail. Our central res...

Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based agents. Although memory is widely used in agent systems, its role in reliable UAQ handling remains unclear. We present a systematic study of agent memory for UAQ handling under a unified agentic RAG framework, evaluating four representative memory methods across three UAQ-related datasets and two base models. We find that memory can improve UAQ performance in some settings, but such gains are selective rat...

No description available

As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures. Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by intent signals in reasoning. However, post-hoc CoT labels are too coarse to show how intent changes during generation. We introduce INTENT-AS-A-TOOL, an approach that adds intent-...

This report presents a framework to help organisations, policymakers and researchers reason about the risks that emerge when AI agents interact with each other, how those risks change as interactions cross organisational boundaries, and the controls that may help address them. As organisations deploy AI agents, those agents will increasingly interact with each other: inside the organisation, with the agents of partners, customers and suppliers, and with unknown counterparties on the open inter...

The potential for AI to automate scientific research and manufacturing must be balanced with new risks, Anthropic says.

Anthropic on September 1, 2026, announced Enterprise Frontier Safeguards (EFS), an offering that combines the privacy of zero data retention with automated safeguards for detecting misuse by storing activity data in cloud infrastructure controlled by the customer rather than by Anthropic. The system will roll out to customers in phases beginning later in the fall of 2026. According to Anthropic, Mythos-class models such as Claude Fable 5.1 represent a major increase in intelligence and agentic…

Presented by EDB As enterprises give AI agents more autonomy — the ability to plan, decide, and act across systems without a human approving each step — a hard question moves to the center of every architecture review: When an agent tries to complete an action that it was never authorized to do, what actually stops it?These are your agents, running on your models, touching your data in your infrastructure — and the responsibility for what they do sits with you. That responsibility can’t be met i

Now exiting stealth mode with a $26 million seed round, Keenable has been building a vast web search index for AI agents.