Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
Paper
• 2510.20150 • Published
• 6
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 • 105 -
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
Paper • 2511.22570 • Published • 90 -
GARDO: Reinforcing Diffusion Models without Reward Hacking
Paper • 2512.24138 • Published • 29 -
Controlled Self-Evolution for Algorithmic Code Optimization
Paper • 2601.07348 • Published • 114 -
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Paper • 2601.18778 • Published • 40 -
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Paper • 2601.14243 • Published • 22 -
VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
Paper • 2601.16973 • Published • 40 -
Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
Paper • 2601.11258 • Published • 9 -
RL's Razor: Why Online Reinforcement Learning Forgets Less
Paper • 2509.04259 • Published • 6 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 139