When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
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. When agent and reference share an unstable rollout transformation, this rule can propagate shared reference failures into broad compliance credit. We audit this risk in NAVSIM v2.2 original
Record details
Published: 5 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Regulation · Agents & autonomy · Transparency
Retrieved: 6 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
arXiv · 6 August 2026
WebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance
arXiv cs.HC · 7 August 2026
FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows
arXiv · 3 August 2026
Governing Agentic AI in FinTech
arXiv · 11 August 2026
Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents
arXiv · 12 August 2026
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
arXiv cs.AI · 29 July 2026
How to cite this record
ethics.ai (5 August 2026), “When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit,” evidence record 16929, https://ethics.ai/record/16929 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.