arXiv:2608. 17597v1 Announce Type: cross Abstract: Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 06984v1 Announce Type: cross Abstract: Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts.
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
arXiv:2607. 01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks.
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.
arXiv:2606. 19380v1 Announce Type: cross Abstract: Software engineering and deployment are increasingly being delegated to AI coding agents.