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.
@article{arxiv.2602.11931,
title = {AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection},
author = {Pretam Ray and Pratik Prabhanjan Brahma and Zicheng Liu and Emad Barsoum},
journal= {arXiv preprint arXiv:2602.11931},
year = {2026}
}