Prime Intellect releases prime-rl 0.10.0 with a new RL loss and unified eval stack
Original titleprime-rl 0.10.0: faster training, our new RL loss IPO, and one unified eval stack
AISummary
Prime Intellect releases prime-rl v0.10.0 and verifiers v0.4.0, making its new IPO loss the default for RL training.
In an agentic SWE RL ablation on GLM-4.5-Air, IcePop collapsed around step 1.2k while IPO at eps 0.3 trained through, masking about 0.25% of tokens versus about 2% at the old 0.1.
The release also adds throughput gains, new model support, and a single uv run eval command for training and standalone evaluation.
AIWhy it matters
The post explains a new RL loss and how it stayed stable where IcePop collapsed, with ablation figures a reader can check against their own training setup.
Source: Prime Intellect Blog · primeintellect.aiPublished · added here