Squeeze Evolve: A Unified Multi-Model Orchestration Framework for Verifier-Free Evolution
Monish Maheswaran ⋅ Leon Lakhani ⋅ Zhongzhu Zhou ⋅ Shijia Yang ⋅ Junxiong Wang ⋅ Coleman R Hooper ⋅ Yuezhou Hu ⋅ Rishabh Tiwari ⋅ Jue WANG ⋅ Harman Singh ⋅ Qingyang Wu ⋅ Ce Zhang ⋅ Kurt Keutzer ⋅ Tri Dao ⋅ Xiaoxia Wu ⋅ Ben Athiwaratkun ⋅ James Zou ⋅ Chenfeng Xu
Abstract
Evolutionary test-time scaling has emerged as a powerful paradigm for improving performance on scientific discovery and other complex reasoning tasks. In this paper, 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 homogeneous, heterogeneous, 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.
Successful Page Load