Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Haolong Qian, Xianliang Yang, Yinuo ma +6
Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher rewar…
cs.AI2026
DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback
Lirong Che, Yuzhe yang, Peiwen lin +4
Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon tasks, each roll…