2 papers
cs.LG2026
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
Jianghao Wu, Jianfei Cai, Weiqiang Wang +3
Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to which instances are used makes…
cs.CL2026
SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization
Jianghao Wu, Yasmeen George, Jin Ye +3
Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent…