Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent dynamically select an LLM that is sufficiently capable for the current generation step while remaining computationally efficient? While model cascades offer a practical mechanism for balancing this trade-off, existing routing strategies typically rely on static heuristics or external controllers and do not explicitly account for model uncertainty. We introduce AdaptEvolve: Adaptive LLM Selection for Multi-LLM Evolutionary Refinement within an evolutionary sequential refinement framework that leverages intrinsic generation confidence to estimate real-time solvability. Empirical results show that confidence-driven selection yields a favourable Pareto frontier, reducing total inference cost by an average of 37.9% across benchmarks while retaining 97.5% of the upper-bound accuracy of static large-model baselines. Our code is available at https://github.com/raypretam/adaptive_llm_selection.

翻译：进化式智能体系统通过在推理过程中反复调用大语言模型（LLM），加剧了计算效率与推理能力之间的权衡。这一设定引出了一个核心问题：智能体如何能动态选择一个在当前生成步骤中能力足够强大，同时仍保持计算效率的LLM？虽然模型级联为平衡这一权衡提供了实用机制，但现有的路由策略通常依赖于静态启发式方法或外部控制器，并未明确考虑模型的不确定性。我们提出了AdaptEvolve：一种在进化式顺序精炼框架内的自适应LLM选择方法，用于多LLM进化精炼，该方法利用内在生成置信度来实时估计问题可解性。实证结果表明，置信度驱动的选择产生了有利的帕累托前沿，在各项基准测试中平均降低了37.9%的总推理成本，同时保留了静态大模型基线97.5%的上界准确率。我们的代码可在 https://github.com/raypretam/adaptive_llm_selection 获取。