End-to-end planners for autonomous driving typically generate a set of candidate trajectories, score each one, and return the highest-scoring candidate. However, the scorer is applied only after the proposals are generated and cannot influence the set of trajectories: a weak set of candidates limits planning performance regardless of the scorer's quality. We instead treat the scorer as a learned trajectory-level reward function and search for trajectories that maximize it. Our method, TOAD, runs the Cross-Entropy Method at test time, warm-started from the planner's proposals. It requires no retraining and is plug-and-play for existing planners. Across six base planners, TOAD improves results on NAVSIM-v1 (94.7 PDMS), NAVSIM-v2 (56.3 EPDMS), and the closed-loop HUGSIM benchmark. The code will be made publicly available via the project page: https://valeoai.github.io/TOAD/.

翻译：自动驾驶的端到端规划器通常生成一组候选轨迹，对每条轨迹进行评分，并返回得分最高的候选轨迹。然而，评分器仅在轨迹生成后应用，无法影响轨迹集合：无论评分器质量如何，较弱的候选集都会限制规划性能。我们转而将评分器视为学习得到的轨迹级奖励函数，并搜索能最大化该奖励的轨迹。我们的方法TOAD在测试时运行交叉熵方法，并从规划器的候选轨迹出发进行热启动。该方法无需重新训练，可直接集成到现有规划器中。在六个基础规划器上，TOAD在NAVSIM-v1（94.7 PDMS）、NAVSIM-v2（56.3 EPDMS）以及闭环HUGSIM基准测试中均提升了性能。代码将通过项目页面公开：https://valeoai.github.io/TOAD/。