RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 9 days ago • 213
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 16 days ago • 248
INT8 LLMs for vLLM Collection Accurate INT8 quantized models by Neural Magic, ready for use with vLLM! • 47 items • Updated Mar 2 • 21
Nemotron Math & Reasoning Collection Datasets for building models that excel at math reasoning, proofs, and quantitative problem-solving. Covers SFT, RL, and pretraining data. • 23 items • Updated Aug 11 • 16