arXiv:2608. 04896v1 Announce Type: new Abstract: Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not.
By Ziang Wei, Minjun Yu, Zheyuan Lai, Mingjie Pang, Wei Li
arXiv:2607. 12469v1 Announce Type: cross Abstract: Many agent-safety evaluation results are not yet load-bearing evidence: identical nominal outcomes (task success, attack success, monitor scores) may sit atop materially different evidence regimes.
By Oleg Solozobov
arXiv:2608. 17713v1 Announce Type: new Abstract: Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral preprocessing.
By Zhen Zhang, Ahmad Hafez, Amr Alanwar
arXiv:2606. 10241v1 Announce Type: new Abstract: Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history.
By Yohei Nakajima
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
arXiv:2606. 31844v1 Announce Type: cross Abstract: A local-to-global context mismatch arises when autoregressive traffic simulators trained on ego-centric driving logs are deployed in globally observable closed-loop environments.
By Ziyan Wang, Tan Xiang, Peng Chen, Xintao Yan