Meta-learning ecological priors from large language models explains human learning and decision making

2025-08-28

AI Summary

Can human learning and decision-making be understood as ecological adaptation to the statistical structure of real-world tasks? This paper introduces the Ecological Rationality Modeling Framework (ERMI), the first approach to integrate large language models (LLMs) with meta-learning to autonomously generate ecologically valid cognitive tasks and acquire ecological priors—without hand-crafted heuristics—enabling flexible generalization to novel contexts. ERMI employs rational analysis and statistical modeling to construct inference mechanisms aligned with natural problem structures, thereby elucidating the ecological adaptation principles underlying cognition. Evaluated across 15 canonical experiments spanning function learning, category learning, and decision-making, ERMI consistently outperforms leading cognitive models. By unifying data-driven task generation with principled Bayesian inference, ERMI establishes a scalable, empirically grounded paradigm for computational cognitive science.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Bayesian Learning
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Human cognition is profoundly shaped by the environments in which it unfolds. Yet, it remains an open question whether learning and decision making can be explained as a principled adaptation to the statistical structure of real-world tasks. We introduce ecologically rational analysis, a computational framework that unifies the normative foundations of rational analysis with ecological grounding. Leveraging large language models to generate ecologically valid cognitive tasks at scale, and using meta-learning to derive rational models optimized for these environments, we develop a new class of learning algorithms: Ecologically Rational Meta-learned Inference (ERMI). ERMI internalizes the statistical regularities of naturalistic problem spaces and adapts flexibly to novel situations, without requiring hand-crafted heuristics or explicit parameter updates. We show that ERMI captures human behavior across 15 experiments spanning function learning, category learning, and decision making, outperforming several established cognitive models in trial-by-trial prediction. Our results suggest that much of human cognition may reflect adaptive alignment to the ecological structure of the problems we encounter in everyday life.

Problem

• Develops ecologically rational meta-learned inference algorithms
• Explains human learning and decision-making across experiments
• Uses large language models to generate ecological cognitive tasks

Innovation

• Meta-learning from LLMs for ecological priors
• Generating ecologically valid tasks at scale
• Deriving rational models optimized for environments