# An active inference model of collective intelligence

arXiv: https://arxiv.org/abs/2104.01066 · HTML: https://mlsanity.com/paper/2104.01066/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 105 references that are in the map.
- First posted on arXiv 2 Apr 2021.

## Builds on (most cited first, 6 of 6)

- [The free energy principle for action and perception: A mathematical review](https://mlsanity.com/paper/1705.09156/) (2017)
- [A free energy principle for a particular physics](https://mlsanity.com/paper/1906.10184/) (2019)
- [A World unto Itself: Human Communication as Active Inference](https://mlsanity.com/paper/1906.10538/) (2019)
- [A Minimal Active Inference Agent](https://mlsanity.com/paper/1503.04187/) (2015)
- [Integrated Information as a Metric for Group Interaction: Analyzing Human and Computer Groups Using a Technique Developed to Measure Consciousness](https://mlsanity.com/paper/1702.02462/) (2017)
- [Agent-based models of collective intelligence](https://mlsanity.com/paper/1810.11634/) (2018)

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

- [Designing Ecosystems of Intelligence from First Principles](https://mlsanity.com/paper/2212.01354/) (2022)
- [Active Inference and Human--Computer Interaction](https://mlsanity.com/paper/2412.14741/) (2024)
- [A Theory of Intelligences](https://mlsanity.com/paper/2308.12411/) (2023)

## Abstract (arXiv)

To date, formal models of collective intelligence have lacked a plausible mathematical description of the relationship between local-scale interactions between highly autonomous sub-system components (individuals) and global-scale behavior of the composite system (the collective). In this paper we use the Active Inference Formulation (AIF), a framework for explaining the behavior of any non-equilibrium steady state system at any scale, to posit a minimal agent-based model that simulates the relationship between local individual-level interaction and collective intelligence (operationalized as system-level performance). We explore the effects of providing baseline AIF agents (Model 1) with specific cognitive capabilities: Theory of Mind (Model 2); Goal Alignment (Model 3), and Theory of Mind with Goal Alignment (Model 4). These stepwise transitions in sophistication of cognitive ability are motivated by the types of advancements plausibly required for an AIF agent to persist and flourish in an environment populated by other AIF agents, and have also recently been shown to map naturally to canonical steps in human cognitive ability. Illustrative results show that stepwise cognitive transitions increase system performance by providing complementary mechanisms for alignment between agents' local and global optima. Alignment emerges endogenously from the dynamics of interacting AIF agents themselves, rather than being imposed exogenously by incentives to agents' behaviors (contra existing computational models of collective intelligence) or top-down priors for collective behavior (contra existing multiscale simulations of AIF). These results shed light on the types of generic information-theoretic patterns conducive to collective intelligence in human and other complex adaptive systems.