When Fitness Scores Mislead: An Empirical Study of LLM-Guided Program Evolution

This preprint reports a bounded empirical audit of evaluator reliability in LLM-guided program evolution with OpenEvolve 0.4.0. It examines circle packing and approximate nearest-neighbour search through a Colab L4 scale study, a Gemma 4 12B laptop pilot, and a separately frozen six-pair evaluator-estimation cohort. The study compares working-evaluator selection with independent verification. In three 1,000-call circle-packing runs, the search found valid improvements that selection failed to retain in two runs. In nine matched kNN runs, cloud-assisted outcomes scored higher in eight pairs after serial re-timing; this comparison is exploratory. A later six-pair cohort selected independently valid programs in 6/6 timing-matched control runs and 5/6 distance-gated runs. The small cohort does not establish an evaluator effect. The results are descriptive and bounded to the tasks, model configurations, and execution conditions studied. They do not establish general scaling laws, a causal benefit of cloud assistance, or general superiority of an evolutionary method. The record contains the English and Ukrainian article PDFs. Reproducibility materials and source files are linked from the repository version recorded with this deposit.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24415799
Primary Topic
Evolutionary Algorithms and Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

When Fitness Scores Mislead: An Empirical Study of LLM-Guided Program Evolution

Pylypenko Oleksandr
Zenodo (CERN European Organization for Nuclear Research)
Evolutionary Algorithms and Applications
preprint

When Fitness Scores Mislead: An Empirical Study of LLM-Guided Program Evolution

Pylypenko Oleksandr
preprint en

Abstract

This preprint reports a bounded empirical audit of evaluator reliability in LLM-guided program evolution with OpenEvolve 0.4.0. It examines circle packing and approximate nearest-neighbour search through a Colab L4 scale study, a Gemma 4 12B laptop pilot, and a separately frozen six-pair evaluator-estimation cohort. The study compares working-evaluator selection with independent verification. In three 1,000-call circle-packing runs, the search found valid improvements that selection failed to retain in two runs. In nine matched kNN runs, cloud-assisted outcomes scored higher in eight pairs after serial re-timing; this comparison is exploratory. A later six-pair cohort selected independently valid programs in 6/6 timing-matched control runs and 5/6 distance-gated runs. The small cohort does not establish an evaluator effect. The results are descriptive and bounded to the tasks, model configurations, and execution conditions studied. They do not establish general scaling laws, a causal benefit of cloud assistance, or general superiority of an evolutionary method. The record contains the English and Ukrainian article PDFs. Reproducibility materials and source files are linked from the repository version recorded with this deposit.

Zenodo (CERN European Organization for Nuclear Research)
State University of Trade and Economics (UA)
Evolutionary Algorithms and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
When Fitness Scores Mislead: An Empirical Study of LLM-Guided Program Evolution — Pylypenko Oleksandr · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS