Study: coding-agent self-evolution works in only 2 of 7 tested /retro changes

dotey · x · 2026-11-04

A paper by Christoph Treude (SMU) and Sebastian Baltes (Heidelberg) tested whether letting Claude Code run /retro after tasks and amend its harness actually helps.

dotey adds: only skills with programmatically verifiable acceptance criteria can self-improve; humans should direct, AI should edit, with version control per iteration.

Related event: Paper Evaluates Self-Evolving Claude Code Skill /retro(3 posts)→

Original post →

More from coding & agent

coding & agent channel →