tencent/VulnGym
Viewer • Updated • 592 • 628 • 8
AI & ML interests
None defined yet.
Recent Activity
Papers
Training the Whole Agent, Not Just the Model
Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
tencent/OSWorkerBench
Viewer • Updated • 4.09k • 1.39k • 7
tencent/MegaStyle-1.4M
Viewer • Updated • 8M • 1.86k • 55
tencent/ElephantBench
Viewer • Updated • 1.09k • 150 • 7
tencent/workbuddy-bench
Updated • 3.48k • 21
tencent/Hy-Embodied-0.5-VLA-Data
Viewer • Updated • 22 • 72.1k • 29
tencent/DiffSpot
Viewer • Updated • 4.4k • 466 • 7
tencent/PlanningBench
Viewer • Updated • 467 • 241 • 12
tencent/IFMTBench
Updated • 208 • 12
tencent/CL-bench-Life
Viewer • Updated • 405 • 222 • 7
tencent/HY3D-Bench
Updated • 34.2k • 96
tencent/Penguin-Recap-V
Viewer • Updated • 4.48M • 69 • 15
tencent/Penguin-Recap-I
Viewer • Updated • 104M • 676 • 18
tencent/RVMS-Bench
Viewer • Updated • 1.44k • 223 • 7
tencent/A.S.E
Preview • Updated • 72 • 5
tencent/AutoCodeBenchmark
Viewer • Updated • 7.51k • 1.58k • 24
tencent/CL-bench
Viewer • Updated • 1.9k • 1.24k • 149
tencent/VCB-Bench
Preview • Updated • 2.61k • 9
tencent/ArtifactsBenchmark
Viewer • Updated • 1.83k • 342 • 13
tencent/WildSpeech-Bench
Viewer • Updated • 1.1k • 245 • 37
tencent/C3-BenchMark
Viewer • Updated • 256 • 356 • 7