Research

Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair

Single source1 source14 Oct 2026

arXiv:2610.15894v1 Announce Type: cross Abstract: Large language model (LLM) code-repair systems fix faulty programs by repeatedly generating and testing revisions.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.15894

← Back to all developments · Signals are a development reported by more than one source. See the methodology.