{"slug": "optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-for-evolutionary", "title": "Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization", "summary": "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.", "body_md": "arXiv:2608.10694v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-for-evolutionary", "canonical_source": "https://www.machinebrief.com/news/optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-fv1f", "published_at": "2026-08-12 04:00:00+00:00", "updated_at": "2026-08-12 05:41:01.566127+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-infrastructure"], "entities": ["arXiv", "GEPA", "HotpotQA", "IFBench", "LiveBench-Math", "HoVer"], "alternates": {"html": "https://wpnews.pro/news/optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-for-evolutionary", "markdown": "https://wpnews.pro/news/optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-for-evolutionary.md", "text": "https://wpnews.pro/news/optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-for-evolutionary.txt", "jsonld": "https://wpnews.pro/news/optimize-cheap-deploy-strong-cost-aware-cross-tier-transfer-for-evolutionary.jsonld"}}