mathematical reasoning 1on-policy distillation 1prefix failure mitigation 1teacher-student models 1trajectory relaying 1
From the 1 of 40 linked papers with an AI index.
Showing cs.AIShow all
3 papers · 1 filter
cs.AI2025
LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
Xingyu Wu, Yuchen Yan, Shangke Lyu +7
Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for…
cs.AI2025
Hierarchical Budget Policy Optimization for Adaptive Reasoning
Shangke Lyu, Linjuan Wu, Yuchen Yan +7
Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reas…
cs.AI2025
Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
Fei Tang, Yongliang Shen, Hang Zhang +7
Humans can flexibly switch between different modes of thinking based on task complexity: from rapid intuitive judgments to in-depth analytical understanding. However, current Graph…