Demystifying Reinforcement Learning in Agentic Reasoning
AI & ML interests
LLM, Diffusion, and Beyond
Recent Activity
Organization Card
Open-source research from Princeton AI Lab
Contact Us: Interested in learning more or getting involved? Reach out to us at [email protected] or visit our website at https://github.com/Gen-Verse.
models
18
Gen-Verse/Qwen3-4B-RA-SFT
4B
•
Updated
•
214
•
2
Gen-Verse/Qwen2.5-7B-RA-SFT
8B
•
Updated
•
17
Gen-Verse/DemyAgent-4B
4B
•
Updated
•
1.34k
•
8
Gen-Verse/TraDo-8B-Thinking
8B
•
Updated
•
801
•
12
Gen-Verse/TraDo-4B-Instruct
4B
•
Updated
•
97
•
9
Gen-Verse/TraDo-8B-Instruct
8B
•
Updated
•
299
•
10
Gen-Verse/MMaDA-8B-MixCoT
Any-to-Any
•
8B
•
Updated
•
7.34k
•
27
Gen-Verse/ReasonFlux-PRM-7B
Text Generation
•
7B
•
Updated
•
625
•
8
Gen-Verse/ReasonFlux-PRM-Qwen-2.5-7B
Text Generation
•
8B
•
Updated
•
6
•
•
3
Gen-Verse/ReasonFlux-PRM-1.5B
Text Generation
•
2B
•
Updated
•
5
•
3
datasets
27
Gen-Verse/Open-AgentRL-30K
Viewer
•
Updated
•
30.1k
•
254
•
2
Gen-Verse/Open-AgentRL-SFT-3K
Viewer
•
Updated
•
3k
•
182
•
2
Gen-Verse/Open-AgentRL-Eval
Viewer
•
Updated
•
433
•
53
Gen-Verse/PrimeIntellect
Viewer
•
Updated
•
5.95k
•
88
Gen-Verse/demon_openr1math
Viewer
•
Updated
•
2k
•
78
Gen-Verse/LiveBench
Viewer
•
Updated
•
128
•
93
Gen-Verse/MATH_train
Viewer
•
Updated
•
8.52k
•
84
Gen-Verse/LiveCodeBench
Preview
•
Updated
•
78
Gen-Verse/AIME2024
Viewer
•
Updated
•
30
•
61
Gen-Verse/GSM8K
Viewer
•
Updated
•
1.32k
•
75