# Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation

arXiv: https://arxiv.org/abs/2404.12056 · HTML: https://mlsanity.com/paper/2404.12056/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 50 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 11 of 11)

- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [RuleMatrix: Visualizing and Understanding Classifiers with Rules](https://mlsanity.com/paper/1807.06228/) (2018)
- [Hybrid Intelligence](https://mlsanity.com/paper/2105.00691/) (2021)
- [VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection](https://mlsanity.com/paper/2009.12975/) (2020)
- [A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization](https://mlsanity.com/paper/2012.00467/) (2020)
- [RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback](https://mlsanity.com/paper/2308.04332/) (2023)
- [Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration](https://mlsanity.com/paper/2309.15723/) (2023)
- [Towards Effective Human-AI Decision-Making: The Role of Human Learning in Appropriate Reliance on AI Advice](https://mlsanity.com/paper/2310.02108/) (2023)
- [A Grammar-Based Approach for Applying Visualization Taxonomies to Interaction Logs](https://mlsanity.com/paper/2201.03740/) (2022)
- [Human-Computer Collaboration for Visual Analytics: an Agent-based Framework](https://mlsanity.com/paper/2304.09415/) (2023)
- [Lotse: A Practical Framework for Guidance in Visual Analytics](https://mlsanity.com/paper/2208.04434/) (2022)

## Built on by (most cited first, 8 of 8)

- [More Human or More AI? Visualizing Human-AI Collaboration Disclosures in Journalistic News Production](https://mlsanity.com/paper/2601.11072/) (2026)
- [LitLinker: Supporting the Ideation of Interdisciplinary Contexts with Large Language Models for Teaching Literature in Elementary Schools](https://mlsanity.com/paper/2502.16097/) (2025)
- [e-person Architecture and Framework for Human-AI Co-adventure Relationship](https://mlsanity.com/paper/2503.22181/) (2025)
- [The Human-Data-Model Interaction Canvas for Visual Analytics](https://mlsanity.com/paper/2505.07534/) (2025)
- [Addressing the Synergy Gap: The Six Elements of the Design Space](https://mlsanity.com/paper/2605.21635/) (2026)
- [Do we have the knowledge we need? Rethinking human-AI decision-making in corporations](https://mlsanity.com/paper/2606.15575/) (2026)
- [Creativity from Friction: Human-AI Interaction for Exploratory Structural Design](https://mlsanity.com/paper/2607.07521/) (2026)
- [Point, Revise, Review: Grounded Agentic Analysis in Reactive Notebooks with marimo-lens](https://mlsanity.com/paper/2609.19839/) (2026)

## Abstract (arXiv)

As full AI-based automation remains out of reach in most real-world applications, the focus has instead shifted to leveraging the strengths of both human and AI agents, creating effective collaborative systems. The rapid advances in this area have yielded increasingly more complex systems and frameworks, while the nuance of their characterization has gotten more vague. Similarly, the existing conceptual models no longer capture the elaborate processes of these systems nor describe the entire scope of their collaboration paradigms. In this paper, we propose a new unified set of dimensions through which to analyze and describe human-AI systems. Our conceptual model is centered around three high-level aspects - agency, interaction, and adaptation - and is developed through a multi-step process. Firstly, an initial design space is proposed by surveying the literature and consolidating existing definitions and conceptual frameworks. Secondly, this model is iteratively refined and validated by conducting semi-structured interviews with nine researchers in this field. Lastly, to illustrate the applicability of our design space, we utilize it to provide a structured description of selected human-AI systems.