Researchers propose TGRL (Temperature-Grouped Reinforcement Learning), a method that groups rollouts by temperature to improve exploration efficiency in reinforcement learning with verifiable rewards …
A new reinforcement learning method called Entropy-Guided Credit Assignment (EGCA) improves exploration in large language model reasoning by assigning credit at a finer granularity without auxiliary m…
A new arXiv paper (2609.28625v1) maps entropy-regularized reinforcement learning with verifiable rewards (RLVR) over myopic tabular policies onto a spin-glass energy model and shows that, for a wide c…
TypeSafe shipped a model called Jev on 15 September 2026 that returns typed answers with probabilities instead of generating text, a category TypeSafe calls a System One model. Jev accepts a state and…
TypeSafe AI introduced a training approach it calls RLCD (reinforcement learning from calibrated decisions), which it says makes models return decisions and probabilities rather than generated text, w…
Researchers introduced PIVOT, a dual-level learning framework that anchors policy optimization around informative visual reasoning signals to improve multimodal reasoning in large vision-language mode…
Researchers introduced MIFS (Multimodal Instruction Following Synthesis), a pipeline that generates RL-ready multimodal data for training generalist agents, producing a dataset of 90k samples across 8…
Researchers introduced DataFlex-RL, an evaluation platform for comparing data policies in reinforcement learning with verifiable rewards (RLVR) under a common GRPO recipe. The platform targets how RLV…
Engineering teams deploying reinforcement learning with verifiable rewards (RLVR) post-training have found that building the training harness accounts for only 20% of the work, with the remaining 80% …
DeepSeek-R1's use of Reinforcement Learning with Verifiable Rewards (RLVR) marks a shift from RLHF's subjective human feedback to deterministic correctness checks, enabling models to reason more relia…
Reinforcement learning for language models has moved from Reinforcement Learning from Human Feedback (RLHF) through LLM-as-a-Judge grading to Reinforcement Learning with Verifiable Rewards (RLVR), whe…
Researchers introduced Energy-Based Fine-Tuning (EBFT), a feature-matching loss that directly aligns a language model's rollout distribution with ground-truth completions in a learned embedding space,…
A large-scale empirical study from arXiv (2608.13698v1) finds that training language models to reason in their native language via Group Relative Policy Optimization (GRPO) leaves only a small gap to …
A new fine-tuning method called 'Advice String Distillation' is proposed as a safer alternative to RLVR for training AI models, using context distillation to update weights with text-associated change…
A new arXiv preprint (2608.02867v1) from researchers studying reinforcement learning with verifiable rewards (RLVR) finds that RLVR-trained large language models (LLMs) exhibit reduced semantic branch…
Researchers propose RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), a method that selectively applies on-policy distillation to negative zero-variance prompts in reinforcement learni…
Researchers propose SAF, a Stable Advantage Fusion framework that combines reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) for training language models, addressi…
Researchers introduced PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework that addresses mode collapse in Large Language Model fi…
Researchers propose a reinforcement learning with verifiable rewards (RLVR) method for data-efficient adaptation of audio-language models to code-switched automatic speech recognition (ASR). Using Qwe…
Researchers formalized medical diagnosis as an iterative evidence-seeking task and used reinforcement learning with verifiable rewards to train large language models to autonomously gather clinical ev…