Models trained by SWE-Master and SWE-World, including both policy models and verifiers.
AI & ML interests
None defined yet.
Recent Activity
Papers
Improving Vision-language Models with Perception-centric Process Reward Models
Towards Long-horizon Agentic Multimodal Search
models 30
RUC-AIBOX/Perceval-3B-reward
4B • Updated • 18
RUC-AIBOX/Perceval-3B-policy
4B • Updated • 21
RUC-AIBOX/ClawGym-30A3
31B • Updated
RUC-AIBOX/ClawGym-8B
8B • Updated • 2
RUC-AIBOX/ClawGym-4B
4B • Updated • 41
RUC-AIBOX/SWE-World-SWR-72B-w-cot
73B • Updated • 1
RUC-AIBOX/SWE-World-SWT-72B-w-cot
73B • Updated • 1
RUC-AIBOX/SWE-World-SWR-32B-w-cot
33B • Updated • 86
RUC-AIBOX/SWE-World-SWT-32B-wo-cot
33B • Updated • 88
RUC-AIBOX/SWE-World-32B-RL
33B • Updated • 5
datasets 19
RUC-AIBOX/ClawGym-Trajectory
Preview • Updated • 194 • 4
RUC-AIBOX/ClawGym-Bench
Viewer • Updated • 200 • 187 • 2
RUC-AIBOX/ClawGym-Task
Preview • Updated • 155 • 6
RUC-AIBOX/OlymMATH
Viewer • Updated • 550 • 1.09k • 14
RUC-AIBOX/Passk_Training_Maze
Viewer • Updated • 40.8k • 17 • 2
RUC-AIBOX/Llama-3-SynE-Dataset
Viewer • Updated • 168M • 231 • 10
RUC-AIBOX/0.8k-data-SimpleDeepSearcher
Viewer • Updated • 871 • 29 • 4
RUC-AIBOX/ORION
Preview • Updated • 26 • 1
RUC-AIBOX/ICPC-Eval
Viewer • Updated • 92 • 406 • 3
RUC-AIBOX/OlymMATH-eval
Viewer • Updated • 579k • 315 • 5