[2602.11931] AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection

Computer Science > Computation and Language arXiv:2602.11931 (cs) [Submitted on 12 Feb 2026 (v1), last revised 24 Apr 2026 (this version, v2)] Title:AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection Authors:Pretam Ray, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum View a PDF of the paper titled AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection, by Pretam Ray and 2 other authors View PDF HTML (experimental) Abstract: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 reta...