arXiv:2607. 06596v1 Announce Type: cross Abstract: Trusted monitoring is a central defense in AI control: a cheaper trusted model scores an untrusted model's actions for sabotage, and the most suspicious are audited or deferred.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2608. 16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost.
arXiv:2607. 13075v1 Announce Type: cross Abstract: Context can change whether a request is harmful without changing its topic or surface form.
arXiv:2606. 10456v1 Announce Type: cross Abstract: AI-control monitors score individual agent actions to detect misbehavior, but real harm can be distributed across many benign-looking steps, each individually below any per-step alarm.
arXiv:2607. 23002v1 Announce Type: cross Abstract: Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified.
arXiv:2607. 11751v1 Announce Type: cross Abstract: As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own.
arXiv:2606. 00813v1 Announce Type: cross Abstract: Safety alignment in LLMs does not improve monotonically across model generations.