While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved. We argue that such problems require human-AI cooperation and that the current state of the art in generative AI is unable to play the role of a reliable partner due to a multitude of shortcomings, including difficulty to keep track of a complex solution artifact (e.g., a software program), limited support for versatile human preference expression and lack of adapting to human preference in an interactive setting. To address these challenges, we propose HAICo2, a novel human-AI co-construction framework. We take first steps towards a formalization of HAICo2 and discuss the difficult open research problems that it faces.
View on arXiv@article{dutta2025_2408.07461,
title={ Problem Solving Through Human-AI Preference-Based Cooperation },
author={ Subhabrata Dutta and Timo Kaufmann and Goran Glavaš and Ivan Habernal and Kristian Kersting and Frauke Kreuter and Mira Mezini and Iryna Gurevych and Eyke Hüllermeier and Hinrich Schuetze },
journal={arXiv preprint arXiv:2408.07461},
year={ 2025 }
}