LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search

TL;DR

LEVI is an evolutionary search framework that leverages stronger search architectures to outperform larger LLMs, achieving high-quality results at significantly lower costs across various benchmarks.

Contribution

LEVI introduces a solution database, a smarter mutation router, and a rank-preserving proxy to enhance evolutionary search efficiency and effectiveness.

Findings

LEVI attains the highest scores on benchmarks with 3.3-6.7x less budget.

On one problem, LEVI matches the best results at 35x lower cost.

LEVI outperforms GEPA at less than half its rollout budget on multiple benchmarks.

Abstract

LLM-guided evolutionary methods such as AlphaEvolve have proven effective in domains like math, systems research, and algorithmic discovery, but their reliance on frontier models makes each run expensive. We argue this is largely an artifact of how existing frameworks allocate search: archives that fail to preserve solution diversity force compensation through stronger mutation models; blind model use spends frontier dollars on local edits a smaller model could handle; and full-set evaluation wastes rollouts on redundant examples. We introduce LEVI, a harness-first evolutionary framework built on the bet that stronger search architectures can substitute for or even outperform larger LLMs in evolutionary search. LEVI improves on three core components of evolutionary search: a solution database that establishes diversity from the beginning, and then maintains it throughout the run; a smarter mutation router that plays into the strengths of large and small LLMs; and a rank-preserving proxy benchmark for rollout-heavy settings. Across systems-research benchmarks LEVI attains the highest score on a budget 3.3-6.7x smaller than the published frontier-model runs of existing frameworks like ShinkaEvolve, GEPA, and AdaEvolve; on one problem, LEVI matches the existing best at a 35x lower cost. On prompt optimization, LEVI matches or exceeds GEPA at less than half of its rollout budget on four different benchmarks. LEVI is available as an open-source framework at https://github.com/ttanv/levi.