Kwai-Klear/SWE-smith-mini_swe_agent_plus-trajectories-66k Viewer • Updated 16 days ago • 66k • 841 • 8
Open Multimodal Retrieval-Augmented Factual Image Generation Paper • 2510.22521 • Published 28 days ago • 30
PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning Paper • 2509.19894 • Published Sep 24 • 33
CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning Paper • 2509.20712 • Published Sep 25 • 19