arxiv:2607.06065
Ruoyu Wang
ruoyu001
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents authored a paper about 2 months ago
What Makes Interaction Trajectories Effective for Training Terminal Agents? updated a model about 2 months ago
Lego-X/SWE-Review-30B-A3BOrganizations
models 18
ruoyu001/swerebench-exp7-mixed-3k-2to1-coderonly-qwen3-8b
308k • Updated • 2
ruoyu001/swerebench-exp7-mixed-6k-qwen3-8b
308k • Updated • 4
ruoyu001/swerebench-exp7-patchgen-3k-qwen3-8b
308k • Updated • 9
ruoyu001/swerebench-exp7-mixed-4k-qwen3-8b
308k • Updated • 4
ruoyu001/swerebench-review-qwen3-30b-a3b-exp0-config-j3-ckpt428
211k • Updated • 2
ruoyu001/swerebench-exp7-patchgen-2k-qwen3-8b
Updated
ruoyu001/swerebench-exp7-review-only-qwen3-8b
308k • Updated • 4
ruoyu001/swerebench-exp7-mixed-qwen3-8b
308k • Updated • 3
ruoyu001/swerebench-exp7-patchgen-only-qwen3-8b
308k • Updated • 5
ruoyu001/swerebench-exp0j3-qwen3-8b
308k • Updated • 3