Loreley system uses Quality-Diversity search for large-scale program evolution

Researchers have developed Loreley, a new system designed for large-scale program evolution using Quality-Diversity (QD) search. Unlike traditional methods that either accumulate changes from a single best version or restart from scratch, Loreley maintains a complete archive of repository states. This allows it to sample past states as parents or provide context for future edits, aiming to improve the breadth of search while retaining progress. Initial experiments comparing Loreley QD with sequential champion editing and independent root proposals showed mixed results, with sequential champion editing performing slightly better at a specific job count. AI

IMPACT Introduces a new method for large-scale program evolution that could enhance software development efficiency.

RANK_REASON The item describes a new research paper detailing a novel algorithm for program evolution. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• CatalyzeX
• DagsHub
• Git
• Gotit.pub
• Hugging Face
• Loreley
• Python
• Quality-Diversity search
• ScienceCast
• Zstandard

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →