On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We introduce ROPD, a rubric-based OPD framework that induces prompt-specific rubrics from teacher-student contrasts and uses them to score student rollouts for on-policy optimization. Empirically, ROPD outperforms advanced logit-based OPD methods across most scenarios and achieves up to a 10x gain in sample efficiency, positioning rubric-based OPD as a flexible, black-box-compatible alternative for scalable distillation across proprietary and open-source LLMs.
Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. We reframe long-horizon agent safety detection as trajectory-level evidence compression and propose Trajectory Risk-Aware Compression for Long-Horizon Agent Safety (TRACE). TRACE uses a Compressor-Reader design: the Compressor encodes the full trajectory into a compact latent evidence state under trajectory-level supervision, and the Reader judges the raw trajectory with this latent evidence state as a safety reference. Across ASSE-Bench, Pre-Ex-Bench, and R-Judge, TRACE achieves the best accuracy on all evaluated backbones, improving over strong baselines by up to 12.6 percentage points. On LongSafety, TRACE shows smaller performance degradation as context length grows.
