On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In this work, we ask a critical research question: Is on-policy sampling always beneficial for distilling arbitrary teacher-student pairs? We show that a simple alternative, Semi-OPD, which distills fro...
Siyan Zhao, Yong-Gan Fu, Jin-Dong Jiang et al.· 2 citations
This work presents VERA, which builds precise and verifiable environments at scale and lets agents evolve on them, and creates a verifier which gates model checkpoints and harness edits using explicit development-set acceptance criteria.
Jun-Qi Liu, Yong-Yang Pan, Zhuo-Song Jiang et al.· 1 citation
Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi-stage and data-sensitive, while expert trajectories remain scarce and difficult to share. Structured benchmarks can localize failures through stage-level rubrics, but...
Junqi Liu, Yu-Fan He, Ye-Xiao He et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.