Reinforcement Learning Gets a New Edge with Reward-Swap Policy Optimization
Reward-Swap Policy Optimization (RSPO) emerges as a promising method to enhance the training of large language models in multi-turn tasks, addressing the challenges of sparse rewards and performance…
Read the full articleYou might also wanna read
ConSPO: A Contrastive Approach to Improving Reinforcement Learning with Verifiable Rewards for LLMs
Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reaso
arxiv.org·1mo ago
Understanding Reinforcement Learning for Model Training, and future directions with GRAPE
This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling,
arxiv.org·9mo ago
MMR-GRPO: Diversity-Aware Reward Reweighting Accelerates Mathematical Reasoning Model Training
Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance o
arxiv.org·1mo ago
Recurrent Structural Policy Gradient: A Method for Partially Observable Mean Field Games
May 2026
Contextual Rollout Bandits: A Neural Scheduling Framework for Efficient Reinforcement Learning with Verifiable Rewards
Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language mo
arxiv.org·1mo ago
Study Finds Single Transformer Layer Can Match Full-Parameter RL Training in LLMs
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how
arxiv.org·9d agoStudy Finds Single Transformer Layer Can Match Full-Parameter RL Training in LLMs
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how
arxiv.org·9d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.