Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
Weiyang Huang, Xuefeng Bai, Kehai Chen +4
Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long reasoning chains. While curren…
cs.AI2026
CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning
Ji Shi, Peiming Guo, Meishan Zhang +4
Code verifiers play a critical role in post-verification for LLM-based code generation, yet existing supervised fine-tuning methods suffer from data scarcity, high failure rates, a…