Hugging Face daily papers·5d agoRRSI: Regularized Recursive Self-Improvement of Agent Harnesses#rrsi#agent-harness#recursive-self-improvement 2 sources
arXiv cs.AI / cs.LG / cs.CL·16d agoDistance generalization in transformers: why bother with positional encoding?#alibi#length-generalization#nopeAI research2