Search papers, labs, and topics across Lattice.
The paper addresses the computational inefficiency of evolutionary AI agents that repeatedly invoke LLMs by proposing AdaptEvolve, a framework for adaptive LLM selection during evolutionary refinement. AdaptEvolve uses intrinsic generation confidence to estimate real-time solvability and dynamically selects an LLM appropriate for the current generation step. Experiments demonstrate that confidence-driven selection achieves a better Pareto frontier, reducing inference costs by 37.9% while maintaining 97.5% of the accuracy of static large models.
Confidence-driven LLM selection slashes inference costs by 37.9% in evolutionary agentic systems, proving you don't need to max out model size for optimal performance.
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.
