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.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simulation benchmarks may use reference-conditioned forgiveness, under which an agent receives credit when the logged human reference fails a compliance channel.
arXiv:2608. 15286v1 Announce Type: cross Abstract: We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated runs, with no LLM in the measurement path, demonstrated on EnterpriseOps-Gym.
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.
arXiv:2606. 10154v1 Announce Type: new Abstract: Quantized checkpoints are often screened first with quality metrics and only later, if at all, with direct safety tests.
arXiv:2608. 14711v1 Announce Type: new Abstract: AI coding agent benchmarks rank agents with the Chen et al.
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.