@@ -131,6 +131,7 @@ verl is inspired by the design of Nemo-Aligner, Deepspeed-chat and OpenRLHF. The
-[DQO](https://arxiv.org/abs/2410.09302): Enhancing multi-Step reasoning abilities of language models through direct Q-function optimization
-[FIRE](https://arxiv.org/abs/2410.21236): Flaming-hot initiation with regular execution sampling for large language models
-[ReSearch](https://github.com/Agent-RL/ReSearch): Learning to **Re**ason with **Search** for LLMs via Reinforcement Learning
-[DeepRetrieval](https://github.com/pat-jj/DeepRetrieval): Let LLMs learn to **search** and **retrieve** desirable docs with RL
## Contribution Guide
Contributions from the community are welcome! Please checkout our [roadmap](https://github.com/volcengine/verl/issues/22) and [release plan](https://github.com/volcengine/verl/issues/354).
