feat: algorithm abstraction — named algorithm classes + inline frozen-model references (grpo, opd, sft_distill, self_distill, echo) by hallerite · Pull Request #2746 · PrimeIntellect-ai/prime-rl
NoteRebased onto verifiers-v1. This PR now targets main after the vf-v1 ⇆ nano bridge (#2742) merged. The branch is a clean 2-commit delta on main (the ~80-file algorithm-abstraction change), repla...
feat: algorithm abstraction — named algorithm classes + inline frozen-model references (grpo, opd, sft_distill, self_distill, echo) by hallerite · Pull Request #2746 · PrimeIntellect-ai/prime-rl · GitHub Skip to content You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Uh oh! There was an error while loading. Please reload this page . PrimeIntellect-ai / prime-rl Public Notifications You must
saved by
related reading
- RL at 1T Scale: prime-rl Performance Deep Diveprimeintellect.ai
- GLM-5.2 RL weight transfer in 4 seconds using NIXL and ModelExpressprimeintellect.ai
- [2604.13010] Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillationarxiv.org
- State of RL for reasoning LLMs | A. Weersaweers.de
- [2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- GRPO++: Tricks for Making RL Actually Workcameronrwolfe.substack.com
- Keep the Tokens Flowing: Lessons from 16 Open-Source RL Librarieshuggingface.co
- [2602.19362] LLMs Can Learn to Reason Via Off-Policy RLarxiv.org
- [2402.14740] Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsarxiv.org
- Reasoning in General Domains without Verifiersarxiv.org
- Prime Agent: A Self-Improving RLM Harnessarxiv.org