Loreley: Repository-Scale Program Evolution with Quality-Diversity Search
Quick summary
arXiv:2608.19703v1 Announce Type: cross Abstract: Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare configured Loreley QD, sequential champion editing, and independent root proposals in a matched Zstandard
Key takeaways
- arXiv:2608.19703v1 Announce Type: cross Abstract: Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root.
- Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits.
- Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator.
Why it matters
“Loreley: Repository-Scale Program Evolution with Quality-Diversity Search” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.
Member comments