# Learning to Chain Operations by Routing Information Through a Global Workspace

arXiv: https://arxiv.org/abs/2503.01906 · HTML: https://mlsanity.com/paper/2503.01906/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Learning to Execute](https://mlsanity.com/paper/1410.4615/) (2014)
- [Coordination Among Neural Modules Through a Shared Global Workspace](https://mlsanity.com/paper/2103.01197/) (2021)
- [Deep Learning and the Global Workspace Theory](https://mlsanity.com/paper/2012.10390/) (2020)
- [Semi-supervised Multimodal Representation Learning through a Global Workspace](https://mlsanity.com/paper/2306.15711/) (2023)

## Built on by (most cited first, 1 of 1)

- [Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form](https://mlsanity.com/paper/2608.15022/) (2026)

## Abstract (arXiv)

We present a model inspired by the Global Workspace Theory that integrates specialized modules to perform a sequential reasoning task. A controller selectively routes information between modules through the workspace using a gating mechanism. This approach allows the model to chain operations by iteratively broadcasting information between specialized domains, mimicking System-2 reasoning. We evaluate the model's performance on a simple addition task, where two addends must be summed. The task can be solved by routing information sequentially through an Input module, an Increment module (multiple times), and finally an Output module. We consider two implementations of this system with increasing complexity. First, using hand-designed modules operating on one-hot digit representations, the controller (a LSTM recurrent network) learns to select the appropriate modules (input, increment, output) in the appropriate sequence. Second, we replace the hand-designed modules with learned representation modules for MNIST images and an increment module trained on the task objectives; here again, the controller learns the appropriate sequential module selection to solve the task. Finally, we show that the Global Workspace model, while having fewer parameters, outperforms LSTMs and Transformers when tested on unseen addition operations (both interpolations and extrapolations of addition operations seen during training). Our results highlight the potential of architectures inspired by the Global Workspace Theory to enhance deep learning's reasoning capabilities.