Squeeze Evolve: A Unified Multi-Model Orchestration Framework for Verifier-Free Evolution

Abstract

We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, while the uniform use of a high-cost model wastes compute and quickly becomes economically impractical. We introduce Squeeze Evolve, a unified multi-model orchestration framework for verifier-free evolutionary inference. Our approach is guided by a simple principle: allocate model capability where it has the highest marginal utility. stronger models are reserved for high-impact stages, while cheaper models handle the other stages at much lower costs. This principle addresses diversity and cost-efficiency jointly while remaining lightweight. Squeeze Evolve naturally supports open-source, closed-source, and mixed-model deployments. Across AIME 2025, HMMT 2025, LiveCodeBench V6, GPQA-Diamond, ARC-AGI-2, multimodal vision benchmarks (MMMU-Pro, BabyVision), and agentic settings (Terminal-Bench~2.0), Squeeze Evolve consistently improves the cost--capability frontier over single-model evolution and achieves new state-of-the-art results on several tasks. Empirically, Squeeze Evolve reduces API cost by up to $\sim$3$\times$ and increases fixed-budget serving throughput by up to $\sim$10$\times$. On circle packing, an open-ended continuous-objective task, Squeeze Evolve is the first verifier-free evolutionary method to exceed AlphaEvolve without executing programs or using closed-weight models.