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:2608. 22915v1 Announce Type: cross Abstract: Inference-time pipelines often sample multiple outputs, filter them with a learned safety model, and return the proxy-feasible output with the highest learned reward.
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
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. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
arXiv:2606. 30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model.
arXiv:2607. 09706v1 Announce Type: new Abstract: Language models turn a worded situation into a numeric plan, and the dominant pipelines (NL4Opt, OptiMUS, ORLM, OR-LLM-Agent) commit to a single objective and point-valued coefficients, then solve once.
arXiv:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
arXiv:2606. 28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf.
arXiv:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box \emph{generators}---are increasingly deployed behind runtim...
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
The paper proves that using a permissive safety filter in reinforcement learning does not compromise asymptotic performance. By formalizing safety through a safety‑critical Markov decision process and a filtered MDP, the authors show that optimal policies in the filtered MDP achieve the same return as the best safe policy in the original setting. Experiments on Safety Gymnasium confirm zero violations during training and performance that matches or exceeds unfiltered baselines.