Minki Kang

Rethinking Reward Models for Multi-Domain Test-Time Scaling

T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models

ACON: Optimizing Context Compression for Long-horizon LLM Agents

Distilling LLM Agent into Small Models with Retrieval and Code Tools

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models