SyncAI.news, a Varaisys broadcasting
Reasoning with Neural Cellular Automata
ME

Mayalen Etcheverry, Pietro Miotti, Aidan Sirbu, Konstantin Sch\"urholt, Mariia Drozdova, Arna Ghosh, Blaise Ag\"uera y Arcas, James Manyika, Blake Richards, Eyvind Niklasson

· 1 min read

ResearcharXiv cs.AI

Reasoning with Neural Cellular Automata

arXiv:2609.36126v1 Announce Type: cross Abstract: Modern AI architectures used to solve visual reasoning tasks typically rely heavily on global connectivity and synchronization. As biological systems demonstrate, though, sophisticated computation can be performed in a more decentralized fashion. In this work, we test the reasoning capabilities of Neural Cellular Automata (NCAs), networks of recurrent cells that use strictly local connectivity and asynchronous updates. NCAs have been extensively studied in artificial life experiments, but it is unclear whether they can perform complex multi-step reasoning. We show that NCAs produce spatio-temporal dynamics capable of solving challenging visual reasoning tasks, including large mazes, Sudoku, and ARC-AGI-1. Furthermore, we provide evidence that NCAs generalize out-of-distribution when running with larger grids, longer rollouts, or parallel trials; and that the latter can be made more efficient via pruning of redundant trajectories. We find that these generalization capabilities depend on training with sample replay and stochastic perturbations, and that stochasticity remains beneficial at test time. Finally, we show that NCAs are robust reasoners capable of dynamically modulating compute to recover efficiently from damage, and that they can scale to solve reasoning in raw pixel space.

Original source

This story was published by arXiv cs.AI and written by Mayalen Etcheverry, Pietro Miotti, Aidan Sirbu, Konstantin Sch\"urholt, Mariia Drozdova, Arna Ghosh, Blaise Ag\"uera y Arcas, James Manyika, Blake Richards, Eyvind Niklasson. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News