11 papers
Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models
Xuning He, Zinan Sheng, Yongding Tao +4
Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irre…
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
Huanyu Liu, Jia Li, Yihong Dong +6
Reinforcement learning with verifiable reward (RLVR) has become a promising paradigm for post-training large language models (LLMs) to improve their reasoning capability. However,…
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
Yihong Dong, Xue Jiang, Yongding Tao +11
Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). However, it struggles to break thro…
VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications
Hao Zhu, Jia Li, Cuiyun Gao +7
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to…
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Yongding Tao, Tian Wang, Yihong Dong +4
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in train…
SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
Huanyu Liu, Ge Li, Jia Li +3
How to design reinforcement learning (RL) tasks that effectively unleash the reasoning capability of large language models (LLMs) remains an open question. Existing RL tasks (e.g.,…