THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper
•
2509.13761
•
Published
•
16
Paper
-
-
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 45 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 23 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 385 -
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
Paper • 2510.03259 • Published • 53 -
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 27