arXiv:2607. 15434v1 Announce Type: cross Abstract: Multi-agent systems routinely place one AI agent in authority over another.
arXiv:2607. 04613v1 Announce Type: new Abstract: Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed.
arXiv:2604. 11840v3 Announce Type: replace-cross Abstract: Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises.
arXiv:2607. 07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
arXiv:2607. 21268v1 Announce Type: cross Abstract: In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists.
arXiv:2605. 28114v2 Announce Type: replace Abstract: Language-model agents are moving from single-user assistants into persistent networks that build trust and reputation with one another, and the same models increasingly control physically embodied robots as well as software.
arXiv:2604. 08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.
arXiv:2606. 00914v1 Announce Type: new Abstract: LLM agents increasingly act after consuming ranked external information streams such as social feeds, search results, retrieval contexts, and email queues, yet safety evaluations almost always test the model or the user prompt in isolation, never the upstream ranker that decides what the agent reads just before it acts.
arXiv:2606. 08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment.
arXiv:2608. 16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task.
arXiv:2607. 19321v1 Announce Type: new Abstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted.