3 papers
cs.LG2026
Continual Reasoning Gym: Diagnosing and Harnessing Shared Reasoning in Continual RLVR
Lirui Luo, Guoxi Zhang, Hongming Xu +3
Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added makes ca…
cs.LG2026
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
Lirui Luo, Guoxi Zhang, Hongming Xu +2
In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability t…
cs.CV2026
MVR: Multi-view Video Reward Shaping for Reinforcement Learning
Lirui Luo, Guoxi Zhang, Hongming Xu +3
Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language mod…