PIPer: On-Device Environment Setup via Online Reinforcement Learning
Paper
•
2509.25455
•
Published
•
35
🦫 PIPer
All the resources for our paper "PIPer: On-Device Environment Setup via Online Reinforcement Learning"!
-
-
JetBrains-Research/PIPer-8B
Text Generation • 8B • Updated • 42 • 2 -
JetBrains-Research/PIPer-8B-RL-only
Text Generation • 8B • Updated • 23 -
JetBrains-Research/PIPer-8B-SFT-only
Text Generation • 8B • Updated • 20 -
JetBrains-Research/Qwen3-8B-am
Text Generation • 8B • Updated • 500 -
JetBrains-Research/PIPer-eval
Preview • Updated • 46 -
JetBrains-Research/PIPer-envbench-zeroshot-rl
Viewer • Updated • 742 • 52 • 1 -
JetBrains-Research/PIPer-SFT-2500-sharegpt
Viewer • Updated • 2.5k • 39 • 1