Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization

ICLR 2026 Conference Submission20066 Authors

Keywords: Mixture of Experts, Functional Specialization, Brain-Inspired AI, Interpretability, Behavioral Alignment

TL;DR: MiCRo is a brain-inspired modular transformer with interpretable experts that match or exceed baselines and can be steered via expert ablations.

Abstract: Human cognitive behavior arises from the interaction of specialized brain networks dedicated to distinct functions, such as language, logic, and social reasoning. Inspired by this organization, we propose Mixture of Cognitive Reasoners (MiCRo): a modular, transformer-based architecture post-trained with a curriculum that induces functional specialization across experts. Concretely, we partition the layers of a pretrained language model into four expert modules aligned with well-studied cognitive networks in the human brain. MiCRo offers three key advantages over standard language models. (1) The specialized experts are interpretable and causally meaningful---ablating a module causes substantial drops on benchmarks requiring its specialized domain. (2) MiCRo's behavior can be dynamically steered at inference time by routing tokens to particular experts (e.g., favoring social over logical reasoning), enabling fine-grained control over outputs. (3) MiCRo outperforms or matches comparable baselines on both machine-learning reasoning benchmarks (e.g., GSM8K, BBH) and alignment to human behavior (CogBench), while maintaining interpretability. Taken together, cognitively grounded functional specialization yields models that are both more human-like and more human-interpretable.

Primary Area: applications to neuroscience & cognitive science

Submission Number: 20066