Recursive Self-Improvement on a Budget: Scoring Code Edits Before They Run

A coding agent that rewrites its own scaffold has to choose which proposed edit to expand before that edit has been evaluated, and the search then has to return one agent. Each run fits one linear readout on the parent's steering-split solve rate and eight coordinates of the proposed diff, from 96 scaffold edits labeled by four evaluations of a 16-instance fit split, and then freezes the…

Publisher's summary from arXiv cs.AI. Read the full article on arXiv cs.AI · More from arXiv cs.AI