Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
Paper
•
2510.20150
•
Published
•
4
RL
-
-
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Paper • 2511.06221 • Published • 132 -
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Paper • 2508.10433 • Published • 144 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 99 -
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
Paper • 2511.22570 • Published • 88 -
GARDO: Reinforcing Diffusion Models without Reward Hacking
Paper • 2512.24138 • Published • 28 -
Controlled Self-Evolution for Algorithmic Code Optimization
Paper • 2601.07348 • Published • 101