Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization

A new arXiv paper (2608.10694v1) proposes a cost-aware cross-tier transfer method for evolutionary optimization of LLM prompts and agentic programs, reducing search cost by 5.6-14x (up to 25-54x with long reasoning chains) while matching or exceeding same-tier optimization across four tasks and eleven models. The approach decouples LLM roles, placing over 96% of search tokens on the cheapest tier and using a strong model only for reflection/variation, then transferring the evolved prompt to a stronger target model.

arXiv:2608.10694v1 Announce Type: new Abstract: Evolutionary optimization of LLM prompts and agentic programs e.g., GEPA is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a validation set, so the evaluator's price tier dictates total search cost. We restructure that search by decoupling the three roles an LLM plays, running the high-volume answering role on the cheapest tier, reserving a strong model for the rare reflection/variation operator, then exploiting upward cross-tier transfer to deploy the cheaply evolved prompt on a stronger target. We contribute a cost-controlled characterization of when cheap-tier search substitutes for target-tier search, and where it fails. Across four tasks HotpotQA, IFBench, LiveBench-Math, HoVer and eleven models in four model families, the resulting prompt matches or exceeds same-tier optimization while placing over 96% of search tokens on the cheapest tier, at 5.6-14x lower search cost, rising to 25-54x where reasoning tiers emit long chains of thought on every fitness call.