EvoHIIT: Preference-Based Selection in LLM-Assisted Evolutionary Design of Natural Language Solutions

Abstract

Large Language Models (LLMs) are increasingly used as generative operators in evolutionary algorithms, yet the role of selection in LLM-assisted systems remains underexplored, particularly when optimizing structured natural language artifacts without ground-truth fitness signals. We introduce EvoHIIT, an LLM-assisted evolutionary framework for the design of High-Intensity Interval Training (HIIT) programs, and study preference-based selection mechanisms. Within an evolutionary loop, EvoHIIT compares four evaluation regimes: (i) scalar fitness based on LLM-predicted physiological and structural proxies, (ii) LLM-based pairwise qualitative selection, (iii) human preference selection, and (iv) hybrid strategies combining automated optimization with periodic human correction. Using schema-constrained HIIT programs as a controlled domain, we analyze convergence dynamics, mutation behavior and alignment with user and expert judgments. Our results show that the choice of selection mechanism substantially shapes search trajectories in semantic solution spaces. While proxy-based scalar fitness enables stable optimization, preference-based selection mitigates specification bias and improves perceived quality. Our findings position selection as a central design dimension in LLM-assisted evolutionary optimization and provide empirical insight into human-aligned evolution of natural language solutions.