2 papers
cs.LG2026
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
Longwen Wang, Yirui Liu, Xuan'er Wu +6
Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but in…
cs.CL2025
Efficient Reasoning via Thought-Training and Thought-Free Inference
Canhui Wu, Qiong Cao, Chao Xue +2
Recent advances in large language models (LLMs) have leveraged explicit Chain-of-Thought (CoT) prompting to improve reasoning accuracy. However, most existing methods primarily foc…