# Interactive inference: a multi-agent model of cooperative joint actions

arXiv: https://arxiv.org/abs/2210.13113 · HTML: https://mlsanity.com/paper/2210.13113/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 76 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 7 of 7)

- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications](https://mlsanity.com/paper/1812.11794/) (2018)
- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [Deep Active Inference](https://mlsanity.com/paper/1709.02341/) (2017)
- [Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework](https://mlsanity.com/paper/2103.02137/) (2021)
- [Emergence of Consensus in a Multi-Robot Network: from Abstract Models to Empirical Validation](https://mlsanity.com/paper/1601.04952/) (2016)
- [Haptic communication optimises joint decisions and affords implicit confidence sharing](https://mlsanity.com/paper/1912.12712/) (2019)

## Built on by (most cited first, 7 of 7)

- [Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following](https://mlsanity.com/paper/2303.15201/) (2023)
- [Theory of Mind Using Active Inference: A Framework for Multi-Agent Cooperation](https://mlsanity.com/paper/2508.00401/) (2025)
- [Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model](https://mlsanity.com/paper/2604.19838/) (2026)
- [Integrating large language models and active inference to understand eye movements in reading and dyslexia](https://mlsanity.com/paper/2308.04941/) (2023)
- [Dynamic planning in hierarchical active inference](https://mlsanity.com/paper/2402.11658/) (2024)
- [CogNarr Ecosystem: Facilitating Group Cognition at Scale](https://mlsanity.com/paper/2407.18945/) (2024)
- [A Computational Model of Inclusive Pedagogy: From Understanding to Application](https://mlsanity.com/paper/2505.02853/) (2025)

## Abstract (arXiv)

We advance a novel computational model of multi-agent, cooperative joint actions that is grounded in the cognitive framework of active inference. The model assumes that to solve a joint task, such as pressing together a red or blue button, two (or more) agents engage in a process of interactive inference. Each agent maintains probabilistic beliefs about the goal of the joint task (e.g., should we press the red or blue button?) and updates them by observing the other agent's movements, while in turn selecting movements that make his own intentions legible and easy to infer by the other agent (i.e., sensorimotor communication). Over time, the interactive inference aligns both the beliefs and the behavioral strategies of the agents, hence ensuring the success of the joint action. We exemplify the functioning of the model in two simulations. The first simulation illustrates a ''leaderless'' joint action. It shows that when two agents lack a strong preference about their joint task goal, they jointly infer it by observing each other's movements. In turn, this helps the interactive alignment of their beliefs and behavioral strategies. The second simulation illustrates a "leader-follower" joint action. It shows that when one agent ("leader") knows the true joint goal, it uses sensorimotor communication to help the other agent ("follower") infer it, even if doing this requires selecting a more costly individual plan. These simulations illustrate that interactive inference supports successful multi-agent joint actions and reproduces key cognitive and behavioral dynamics of "leaderless" and "leader-follower" joint actions observed in human-human experiments. In sum, interactive inference provides a cognitively inspired, formal framework to realize cooperative joint actions and consensus in multi-agent systems.