Skip to content

Author

Hyung Bin Park

We have 2 of 160 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Persistent Teacher Anchoring for Tool-Using Agents

Persistent Teacher Anchoring (PTA) is proposed, a student-induced but teacher-committed rollout construction that retains chunk-level verification and adds turn-level commitment, allowing a call to reach the environment only after the teacher has verified the entire turn.

Hyung Bin Park, Kyung-dong Song, Sang-Min Lee et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO

RL-based post-training for reasoning models is increasingly bottlenecked by repeated fresh rollout generation, particularly in agentic settings where environment interaction dominates wall-clock cost. Replay can reduce this burden by reusing past trajectories, but existing methods typically embed it within larger train...

Hyung Bin Park, Du-seong Chang · 1 citation · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.