GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving Paper • 2510.11769 • Published 15 days ago • 25
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning Paper • 2510.12693 • Published 14 days ago • 26
Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training Paper • 2510.04996 • Published 22 days ago • 15
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning Paper • 2509.25760 • Published 28 days ago • 53
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training Paper • 2509.03403 • Published Sep 3 • 21
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models Paper • 2506.18945 • Published Jun 23 • 40
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2 • 185
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models Paper • 2505.24864 • Published May 30 • 138
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL Paper • 2505.02391 • Published May 5 • 25
CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training Paper • 2504.13161 • Published Apr 17 • 93
Predictive Data Selection: The Data That Predicts Is the Data That Teaches Paper • 2503.00808 • Published Mar 2 • 56
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning Paper • 2403.17919 • Published Mar 26, 2024 • 16