Problem Solving Through Human-AI Preference-Based Cooperation

Authors

  • Subhabrata Dutta TU Darmstadt
  • Tmo Kaufman LMU Munich
  • Goran Glavaš University of Würzburg
  • Ivan Habernal RU Bochum
  • Kristian Kersting TU Darmstadt
  • Frauke Kreuter LMU Munich
  • Mira Mezini TU Darmstadt
  • Iryna Gurevych TU Darmstadt
  • Eyke Hüllermeier LMU Munich
  • Hinrich Schuetze LMU Munich

Keywords:

Preference learning, Expert domain, Co-construction, Human-AI interaction, Search policy, Generative AI, Large Language Models (LLMs)

Abstract

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 inability 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 HAI-Co2, a novel human-AI co-construction framework. We formalize HAI-Co2 and discuss the difficult open research problems that it faces. Finally, we present a case study of HAI-Co2 and demonstrate its efficacy compared to monolithic
generative AI models.

Downloads

Published

2026-01-22

Issue

Vol. 51 No. 4 (2025): Computational Linguistics

Section

Position Paper