Princeton-AI
Open-source research from Princeton AI Lab, led by Ling Yang and Mengdi Wang
Pinned Loading
Repositories
Showing 10 of 13 repositories
- Open-AgentRL Public
An open-source RL (DemyAgent & RLAnything) for training LLM-based agents — supporting GRPO, PPO, RLHF, multi-turn reasoning, tool use, and distributed training.
Gen-Verse/Open-AgentRL’s past year of commit activity - dLLM-RL Public
[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.
Gen-Verse/dLLM-RL’s past year of commit activity - ReasonFlux Public
[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.
Gen-Verse/ReasonFlux’s past year of commit activity - HermesFlow Public
[NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
Gen-Verse/HermesFlow’s past year of commit activity - CURE Public
[NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
Gen-Verse/CURE’s past year of commit activity