# TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution

arXiv: https://arxiv.org/abs/2604.18607 · HTML: https://mlsanity.com/paper/2604.18607/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Evolution through Large Models](https://mlsanity.com/paper/2206.08896/) (2022)
- [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [ThetaEvolve: Test-time Learning on Open Problems](https://mlsanity.com/paper/2511.23473/) (2025)
- [Large Language Models As Evolution Strategies](https://mlsanity.com/paper/2402.18381/) (2024)
- [CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization](https://mlsanity.com/paper/2510.14150/) (2025)
- [LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm](https://mlsanity.com/paper/2512.24077/) (2025)
- [GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms](https://mlsanity.com/paper/2511.17592/) (2025)
- [Self-Adjusting Population Sizes for Non-Elitist Evolutionary Algorithms: Why Success Rates Matter](https://mlsanity.com/paper/2104.05624/) (2021)

## Built on by (most cited first, 3 of 3)

- [Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection](https://mlsanity.com/paper/2608.20169/) (2026)
- [GEAR: Genetic AutoResearch for Agentic Code Evolution](https://mlsanity.com/paper/2605.13874/) (2026)
- [Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility](https://mlsanity.com/paper/2607.26828/) (2026)

## Abstract (arXiv)

LLM-driven program evolution can discover high-quality programs, but high API cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutionary framework that improves sample efficiency and stability under matched API-cost budgets. Inspired by multiple-offspring strategies in evolutionary algorithms, TurboEvolve introduces Verbalized Sampling, which elicits K diverse candidates in one LLM call while using self-assigned probabilities only as generation signals, together with an online scheduler that adapts K to expand exploration under stagnation and reduce redundant generation during steady progress. To exploit existing solution pools, TurboEvolve further introduces island-aware initialization, which clusters seed programs into mode-specific subpopulations and applies controlled cross-cluster mixing with elitist preservation to balance diversity, sharing, and refinement. We also curate a reusable cross-task solution-pool dataset to support warm-start initialization studies and matched-resource comparisons. Across mathematical discovery and GPU-kernel optimization tasks, TurboEvolve achieves stronger cost-quality trade-offs and more stable performance than controlled baselines, while reaching competitive reported scores.