Every 28 Days the AI Dreams of Soft Skin and Burning Stars: Scaffolding AI Agents with Hormones and Emotions
This addresses the fundamental challenge of contextual relevance in AI systems, though it appears incremental as a novel method for a known bottleneck.
The paper tackles the frame problem in AI by embedding simulated hormonal cycles into Large Language Models, finding that performance on benchmarks like SQuAD and MMLU shows subtle but consistent variations aligned with biological phases.
Despite significant advances, AI systems struggle with the frame problem: determining what information is contextually relevant from an exponentially large possibility space. We hypothesize that biological rhythms, particularly hormonal cycles, serve as natural relevance filters that could address this fundamental challenge. We develop a framework that embeds simulated menstrual and circadian cycles into Large Language Models through system prompts generated from periodic functions modeling key hormones including estrogen, testosterone, and cortisol. Across multiple state-of-the-art models, linguistic analysis reveals emotional and stylistic variations that track biological phases; sadness peaks during menstruation while happiness dominates ovulation and circadian patterns show morning optimism transitioning to nocturnal introspection. Benchmarking on SQuAD, MMLU, Hellaswag, and AI2-ARC demonstrates subtle but consistent performance variations aligning with biological expectations, including optimal function in moderate rather than extreme hormonal ranges. This methodology provides a novel approach to contextual AI while revealing how societal biases regarding gender and biology are embedded within language models.