Lego-X/qwen3_5_35b_a3b_ohsdk_200k_rl
Text Generation • 36B • Updated • 465 • 3
Lego-RL
Harness-native RL for coding agents: the trained policy and the training task index.
-
-
Lego-X/Lego-RL-2699
Viewer • Updated • 2.7k • 119 • 2 -
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
Paper • 2608.17393 • Published • 24 -
Lego-X/qwen3_5_35b_a3b_cc_200k_rl
Text Generation • 36B • Updated • 273 • 1 -
Lego-X/qwen3_5_35b_a3b_oc_200k_rl
Text Generation • 36B • Updated • 273 • 1
Lego-X/Lego-RL-SWE-Bench-Verified
Viewer • Updated • 500Note Evaluation set: the 500 SWE-bench Verified instances as harbor RL environments.