cross-tokenizer 1language model distillation 1large language models 1on-policy learning 1reinforcement learning framework 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CL2026
EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models
Jie Sun, Mao Zheng, Mingyang Song +7
The paper introduces EasyOPD, a modular framework that simplifies on-policy distillation for large language models by separating configuration, supervision logic, and distributed e…
cs.AI2026
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
Zhepei Hong, Lin Wang, Liting Li +5
Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level o…
cs.LG2026
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
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 contend that struct…