2 papers
cs.CL2026
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through compl…
cs.CL2026
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
Zhaoyi Li, Deyang Kong, Yuan Wei +13
On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly unders…