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

​Kicking off our seminar series!

We have Temoor Tanveer, almuni Carnegie Mellon University, now an independent researcher

He will be talking about his work:
https://arxiv.org/pdf/2605.09764
https://github.com/ttanv/levi

The talk will cover the he idea behind LEVI, the core architecture, findings from the paper, what leads to savings etc

​And then towards the end I might a few minutes of a real LEVI demo on a problem

Abstract for talk:
LLM-guided evolutionary methods such as AlphaEvolve have proven effective in different domains, 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: github.com/ttanv/levi.