Modular Cognitive Architecture Emerges in Large Language Models
Source
Pengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda
Author
Pengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda
Date
Why it matters
If task families recruit distinct neuron populations, that is a handle for interpretability work, targeted editing, and reasoning about which capabilities interfere. It reframes model internals as modular rather than uniformly entangled.
articleRecursive Language Models Generalize Out of DomainChenxiao Yang, Zhiyuan Li, David McAllester, Nathan Srebro
articleTowards a Characterization of Microservice Architectures Generated by Large Language ModelsJos\'e Renan, Ademar Sousa, Emanuel Dantas, Danyllo Albuquerque, Mirko Perkusic, Kyller Gorg\^onio, Angelo Perkusich
articleInduction and Inquiry via Probabilistic Reasoning over Language and CodeWasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld, Joshua Tenenbaum, Kevin Ellis