# Co-Creative Learning via Metropolis-Hastings Interaction between Humans and AI

arXiv: https://arxiv.org/abs/2506.15468 · HTML: https://mlsanity.com/paper/2506.15468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Delving into LLM-assisted writing in biomedical publications through excess vocabulary](https://mlsanity.com/paper/2406.07016/) (2024)
- [Machine Culture](https://mlsanity.com/paper/2311.11388/) (2023)
- [A survey of multimodal deep generative models](https://mlsanity.com/paper/2207.02127/) (2022)
- [Symbol Emergence in Cognitive Developmental Systems: a Survey](https://mlsanity.com/paper/1801.08829/) (2018)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Symbol Emergence in Robotics: A Survey](https://mlsanity.com/paper/1509.08973/) (2015)
- [Superhuman Artificial Intelligence Can Improve Human Decision Making by Increasing Novelty](https://mlsanity.com/paper/2303.07462/) (2023)
- [Human-AI Coevolution](https://mlsanity.com/paper/2306.13723/) (2023)
- [Empirical evidence of Large Language Model's influence on human spoken communication](https://mlsanity.com/paper/2409.01754/) (2024)
- [Is ChatGPT Transforming Academics' Writing Style?](https://mlsanity.com/paper/2404.08627/) (2024)
- [Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models](https://mlsanity.com/paper/2205.12392/) (2022)
- [Symbol Emergence as an Interpersonal Multimodal Categorization](https://mlsanity.com/paper/1905.13443/) (2019)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Models](https://mlsanity.com/paper/2305.19761/) (2023)
- [Metropolis-Hastings algorithm in joint-attention naming game: Experimental semiotics study](https://mlsanity.com/paper/2305.19936/) (2023)
- [Human-Robot Creative Interactions (HRCI): Exploring Creativity in Artificial Agents Using a Story-Telling Game](https://mlsanity.com/paper/2202.03702/) (2022)
- [Human-AI ecosystem with abrupt changes as a function of the composition](https://mlsanity.com/paper/2204.03372/) (2022)

## Abstract (arXiv)

We propose co-creative learning as a novel paradigm where humans and AI, i.e., biological and artificial agents, mutually integrate their partial perceptual information and knowledge to construct shared external representations, a process we interpret as symbol emergence. Unlike traditional AI teaching based on unilateral knowledge transfer, this addresses the challenge of integrating information from inherently different modalities. We empirically test this framework using a human-AI interaction model based on the Metropolis-Hastings naming game (MHNG), a decentralized Bayesian inference mechanism. In an online experiment, 69 participants played a joint attention naming game (JA-NG) with one of three computer agent types (MH-based, always-accept, or always-reject) under partial observability. Results show that human-AI pairs with an MH-based agent significantly improved categorization accuracy through interaction and achieved stronger convergence toward a shared sign system. Furthermore, human acceptance behavior aligned closely with the MH-derived acceptance probability. These findings provide the first empirical evidence for co-creative learning emerging in human-AI dyads via MHNG-based interaction. This suggests a promising path toward symbiotic AI systems that learn with humans, rather than from them, by dynamically aligning perceptual experiences, opening a new venue for symbiotic AI alignment.