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

• URL: http://arxiv.org/abs/2604.07725v2
• Date: Fri, 10 Apr 2026 17:54:26 GMT
• Title: Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
• Abstract summary: We introduce Squeeze Evolve, a unified multi-model orchestration framework for verifier-free evolutionary inference.<n>Our approach is guided by a simple principle: allocate model capability where it has the highest marginal utility.
• Score: 81.46210789228296
• License: http://creativecommons.org/licenses/by/4.0/
• 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-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.

Related papers

• Self-Evolving Memory for Generative Recommendation [100.15207958893029]
  Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation.<n>Existing evolving strategies, such as continual retraining and distillation-based adaptation, directly update the shared model parameters.<n>We propose a self-evolving memory paradigm for generative recommendation, aiming to enable effective evolution across heterogeneous behavioral patterns.
  arXiv  Detail & Related papers  (2026-09-14T14:00:38Z)
• Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution [32.25060721536872]
  Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery.<n>We propose textbfmodel, a training-free framework that shifts budget allocation from individual calls to evolving populations.<n>Our results suggest that in stateful search, budget allocation should be organized around the population, not the individual call.
  arXiv  Detail & Related papers  (2026-08-06T06:48:08Z)
• Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation [42.09919382465098]
  Large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets.<n>Existing frameworks typically treat these two evolutionary processes in isolation.<n>We introduce a novel paradigm of co-evolutionary Capability Expansion and Experience Distillation.
  arXiv  Detail & Related papers  (2026-04-13T02:44:54Z)
• The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems [55.28554025674495]
  We improve efficiency while preserving the strengths of collaboration by distilling collaborative patterns into a single model.<n>We propose the single-multi evolution loop: multiple LMs collaborate, each distills from the collaborative outputs, and these post-distillation improved LMs collaborate again.
  arXiv  Detail & Related papers  (2026-02-05T01:20:32Z)
• EvoRoute: Experience-Driven Self-Routing LLM Agent Systems [100.64399490164959]
  EvoRoute is a self-evolving model routing paradigm that transcends static, pre-defined model assignments.<n> Experiments on challenging agentic benchmarks demonstrate that EvoRoute, when integrated into off-the-shelf agentic systems, not only sustains or enhances system performance but also reduces execution cost by up to $80%$ and latency by over $70%$.
  arXiv  Detail & Related papers  (2026-01-06T04:06:46Z)
• LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm [8.050281821865978]
  LoongFlow is a self-evolving agent framework that achieves state-of-the-art solution quality with significantly reduced computational costs.<n>Unlike "blind" mutation operators, LoongFlow integrates Large Language Models into a cognitive "Plan-Execute-Summarize" (PES) paradigm.<n>To sustain long-term architectural coherence, we incorporate a hybrid evolutionary memory system.
  arXiv  Detail & Related papers  (2025-12-30T08:39:28Z)
• ThetaEvolve: Test-time Learning on Open Problems [110.5756538358217]
  We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time.<n>We find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines.
  arXiv  Detail & Related papers  (2025-11-28T18:58:14Z)
• EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards [52.42920996842378]
  We propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model.<n>This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning.<n>Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM.
  arXiv  Detail & Related papers  (2025-11-20T18:59:54Z)
• Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation [74.75716642635484]
  Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR)<n>We propose EVOL-RL, a label-free framework that mirrors the evolutionary principle of balancing selection with variation.<n>EVOL-RL consistently outperforms the majority-only baseline.
  arXiv  Detail & Related papers  (2025-09-18T17:50:04Z)
• MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs [14.791853860278914]
  We introduce MERGE$3$, an efficient framework that makes evolutionary merging feasible on a single GPU.<n>MerGE$3$ achieves this by Extracting a reduced dataset for evaluation, Estimating model abilities using Item Response Theory (IRT), and Evolving optimal merges via IRT-based performance estimators.<n>Our method enables state-of-the-art multilingual and cross-lingual merging, transferring knowledge across languages with significantly lower computational overhead.
  arXiv  Detail & Related papers  (2025-02-09T14:24:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.