Search papers, labs, and topics across Lattice.
This paper introduces FrugalEvo, a cost-aware LLM-guided evolutionary framework that leverages a hierarchical LLM approach (stronger LLM for strategy, cheaper LLM for implementation and refinement) to optimize performance gain per unit cost. It also incorporates a cache-efficient evolution process and a Budget-Aware Area Under the Curve (BA-AUC) metric to evaluate solution quality within a fixed cost budget. FrugalEvo achieves state-of-the-art or competitive results across multiple optimization tasks, significantly outperforming existing methods in cost-effectiveness, particularly on challenging problems like circle packing.
Achieve state-of-the-art LLM-guided program evolution for under $2, drastically cutting costs for complex optimization tasks.
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize gain per unit cost. To this end, we propose FrugalEvo, a cost-aware evolutionary framework where a stronger, higher-cost LLM explores solution strategies, and a cheaper LLM implements them and iteratively refines the resulting code. We also design a cache-efficient evolution process, where our harness and prompts maximize the sharing of prefixes across different evolution steps, to improve cache reuse. To measure solution quality throughout a fixed cost budget, we introduce Budget-Aware Area Under the Curve (BA-AUC), defined as the area under the best-so-far evaluation score curve over cumulative LLM cost, up to the budget. Across 10 mathematical and systems optimization tasks, FrugalEvo matches or surpasses state-of-the-art baselines, including OpenEvolve, ShinkaEvolve, AdaEvolve, and EvoX, in final solution quality and achieves higher BA-AUC on 9 tasks. It also achieves higher average performance than these baselines on 10 algorithmic optimization tasks from ALE-Bench-Lite. Notably, on circle packing, FrugalEvo achieves new state-of-the-art performance with GPT-5.6 Terra and Luna for only 1.68 USD and with GLM-5.3 and its Flash variant for only 0.55 USD, matching or surpassing all baselines, including multi-agent methods such as CORAL and SwarmResearch, which cost approximately 50 USD on average.
