JinnP/SGLang-EAGLE3-Qwen3-Coder-30B-A3B-Instruct Text Generation • 0.2B • Updated Nov 25, 2025 • 121 • 1
JinnP/SGLang-EAGLE3-Qwen3-Coder-30B-A3B-Instruct Text Generation • 0.2B • Updated Nov 25, 2025 • 121 • 1
Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs Paper • 2509.25779 • Published Sep 30, 2025 • 19