# A Unified Theory of Dual-Process Control

arXiv: https://arxiv.org/abs/2211.07036 · HTML: https://mlsanity.com/paper/2211.07036/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2022.

## Built on by (most cited first, 3 of 3)

- [Program-Based Strategy Induction for Reinforcement Learning](https://mlsanity.com/paper/2402.16668/) (2024)
- [Principles of frugal inference and control](https://mlsanity.com/paper/2406.14427/) (2024)
- [Knowledge-informed Bidding with Dual-process Control for Online Advertising](https://mlsanity.com/paper/2603.04920/) (2026)

## Abstract (arXiv)

Dual-process theories play a central role in both psychology and neuroscience, figuring prominently in fields ranging from executive control to reward-based learning to judgment and decision making. In each of these domains, two mechanisms appear to operate concurrently, one relatively high in computational complexity, the other relatively simple. Why is neural information processing organized in this way? We propose an answer to this question based on the notion of compression. The key insight is that dual-process structure can enhance adaptive behavior by allowing an agent to minimize the description length of its own behavior. We apply a single model based on this observation to findings from research on executive control, reward-based learning, and judgment and decision making, showing that seemingly diverse dual-process phenomena can be understood as domain-specific consequences of a single underlying set of computational principles.