3 papers
cs.CL2026
Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders
Zichao Yu, Qianshuo Ye, Xu Wang +1
On-policy distillation (OPD) is a widely adopted post-training technique for LLM reasoning. It is commonly believed to transfer knowledge from a stronger teacher, yet what OPD actu…
cs.LG2025
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Xingyue Huang, Rishabh, Gregor Franke +43
Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RL…
cs.AI2025
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Mengkang Hu, Yuhang Zhou, Wendong Fan +13
Large Language Model (LLM)-based multi-agent systems show promise for automating real-world tasks but struggle to transfer across domains due to their domain-specific nature. Curre…