3 papers
cs.AI2026
SHAPE of Chain-of-Thought in Math Reasoning
Jonghyun Song, Sangjun Song, Minjae Oh +3
Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their reasoning remain underexplor…
cs.CL2026
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
Woojung Song, Nalim Kim, Sangjun Song +3
Role-playing language agents (RPLAs) simulate specific characters and personas across applications such as entertainment, companionship, interactive storytelling, and education. Fa…
cs.LG2026
KL for a KL: On-Policy Distillation with Control Variate Baseline
Minjae Oh, Sangjun Song, Gyubin Choi +2
On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice…