arXiv:2606. 08919v1 Announce Type: new Abstract: As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop approval gate: risky actions pause and wait for a person.
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:2608. 06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias.
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.
arXiv:2606. 00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.
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:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv:2608. 16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task.
arXiv:2606. 06529v1 Announce Type: new Abstract: An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately.
arXiv:2606. 08539v1 Announce Type: new Abstract: AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate.
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.
A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps a growing library from drifting below the no-skill baseline, but its guarantee assumes an unbiased reward, which is false for the LLM judges that reference-free tasks force upon us.