Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Paper • 2603.24472 • Published Mar 25 • 57
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization Paper • 2602.23008 • Published Feb 26 • 37
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views Paper • 2510.18632 • Published Oct 21, 2025 • 23
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding Paper • 2508.02215 • Published Aug 4, 2025 • 12
Agent Lightning: Train ANY AI Agents with Reinforcement Learning Paper • 2508.03680 • Published Aug 5, 2025 • 141
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Paper • 2505.12929 • Published May 19, 2025 • 3
