analiza aiqbench
This research paper investigates the structural dynamics of human-AI collaboration, moving beyond simple performance metrics to analyze design tensions regarding autonomy and initiative. By mapping these conflicts through a paradox framework, the authors define four distinct interaction patterns—Instruction, Delegation, Assistance, and Co-creation—that offer a taxonomy for building more effective hybrid systems. The work provides critical theoretical grounding for engineers and researchers aiming to optimize the integration of AI agents into human workflows.
Human-AI Collaboration: From Paradoxes to Patterns
arXiv:2609.36481v1 Announce Type: new Abstract: Evidence shows that humans and AI systems perform better together, by collaborating, than alone. This paper examines two key design dimensions of human-AI collaboration (autonomy and initiative) and explores the collaboration patterns that they generate. Documenting these patterns starts with identifying the underlying problems and solutions, followed by examining the internal tensions within the problems. The paper uses a paradox perspective to analyze those tensions. It describes a process for surfacing the tensions and mapping the underlying paradoxes. It also illustrates how the pattern descriptions can be derived from mapping these paradoxes. Finally, the paper documents four human-AI collaboration patterns: Instruction, Delegation, Assistance, and Co-creation.
Abstract:Evidence shows that humans and AI systems perform better together, by collaborating, than alone. This paper examines two key design dimensions of human-AI collaboration (autonomy and initiative) and explores the collaboration patterns that they generate. Documenting these patterns starts with identifying the underlying problems and solutions, followed by examining the internal tensions within the problems. The paper uses a paradox perspective to analyze those tensions. It describes a process for surfacing the tensions and mapping the underlying paradoxes. It also illustrates how the pattern descriptions can be derived from mapping these paradoxes. Finally, the paper documents four human-AI collaboration patterns: Instruction, Delegation, Assistance, and Co-creation.
This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record will be published in 33rd Conference on Pattern Languages of Programs (PLoP 2026)
Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
arXiv:2609.36481 [cs.AI]
(or arXiv:2609.36481v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.36481 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 242 cuvinte
