arXiv:2608. 13345v1 Announce Type: new Abstract: Artificial Intelligence (AI) safety systems combine character shaping (e.
arXiv:2410. 22526v2 Announce Type: replace Abstract: To effectively address potential harms from Artificial Intelligence (AI) systems, it is essential to identify and mitigate system-level hazards.
arXiv:2607. 16112v1 Announce Type: new Abstract: Frontier AI companies have published capability thresholds that differ substantially, making it difficult for third parties to verify whether a threshold has been crossed or to compare requirements across companies.
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:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
arXiv:2603. 10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost distribution and fails to account for distributional uncertainty, particularly under heavy tails or rare catastrophic events.
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
arXiv:2606. 04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5 models (12B--70B) in 4,200 interactions with dual-judge validation.
arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.
arXiv:2608. 11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.
arXiv:2606. 20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized.
arXiv:2607. 22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech.