Subject
8 open-access journal articles on reinforcement learning with verifiable rewards, published in 2026 in Life of Research. Every record is free to read and download, with a permanent link and a ready-made citation.
Journal article
Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy RL is implicitly biased toward…
Journal article
Curriculum learning entered large-scale reasoning training through reinforcement learning with verifiable rewards (RLVR): difficulty-ordered or difficulty-filtered problem schedules are now routine in systems built on GRPO and DAPO, and dozens of 2024-2026 papers report a gain from some version of…
Journal article
Between 2025 and 2026 at least six frameworks added an intrinsic novelty or uncertainty term to reinforcement learning with verifiable rewards for language models, each naming a classical antecedent - prediction error, pseudo-counts, epistemic uncertainty - and each reporting gains. The classical…
Journal article
Between 2025 and 2026 at least six frameworks added an intrinsic novelty or uncertainty term to reinforcement learning with verifiable rewards for language models, each naming a classical antecedent - prediction error, pseudo-counts, epistemic uncertainty - and each reporting gains. The classical…
Journal article
Reinforcement learning with verifiable rewards is the standard route to reasoning-tuned language models, and the field has split over whether its gains leave the training domain. One body of work reports that most models succeeding at mathematics fail to transfer and that single-domain…
Journal article
Reinforcement learning with verifiable rewards is the standard route to reasoning-tuned language models, and the field has split over whether its gains leave the training domain. One body of work reports that most models succeeding at mathematics fail to transfer and that single-domain…
Journal article
A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing about which direction the boundary moved. This paper…
Journal article
A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing about which direction the boundary moved. This paper…