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-V2, and multimodal vision benchmarks, such as MMMU-Pro and BabyVision, 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$. Moreover, on discovery tasks, Squeeze Evolve is the first verifier-free evolutionary method to match, and in some cases exceed, the performance of verifier-based evolutionary methods.

翻译：我们证明，免验证器进化受到多样性和效率的双重瓶颈制约：在没有外部校正的情况下，重复进化会加速向狭窄模式坍缩，而统一使用高成本模型浪费计算资源且在经济上迅速变得不可行。我们提出挤压进化——一种用于免验证器进化推理的统一多模型编排框架。该框架遵循一个简单原则：将模型能力分配至边际效用最高的环节。强模型保留用于高影响阶段，而廉价模型则以极低成本处理其他阶段。该原则在保持轻量性的同时联合解决了多样性与成本效率问题。挤压进化原生支持开源、闭源及混合模型部署。在AIME 2025、HMMT 2025、LiveCodeBench V6、GPQA-Diamond、ARC-AGI-V2以及MMMU-Pro和BabyVision等多模态视觉基准测试中，挤压进化持续改进了单模型进化的成本-能力边界，并在多个任务上取得新最优结果。实验表明，挤压进化可将API成本降低约3倍，并将固定预算的服务吞吐量提升约10倍。此外，在探索性任务中，挤压进化是首个达到甚至超越基于验证器的进化方法性能的免验证器进化方法。