Problem Solving Through Human-AI Preference-Based Cooperation

MCML Authors

Timo Kaufmann

→ Group Eyke Hüllermeier
 Artificial Intelligence and Machine Learning

Frauke Kreuter

Prof. Dr.

Principal Investigator

Social Data Science and AI

Eyke Hüllermeier

Prof. Dr.

Principal Investigator

Artificial Intelligence and Machine Learning

Hinrich Schütze

Prof. Dr.

Principal Investigator

Computational Linguistics

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 difficulty in keeping 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 take first steps towards a formalization of HAI-Co2 and discuss the difficult open research problems that it faces.

article

---

Computational Linguistics

Sep. 2025.

---

Authors

S. Dutta • T. Kaufmann • G. Glavaš • I. Habernal • K. Kersting • F. Kreuter • M. Mezini • I. Gurevych • E. Hüllermeier • H. Schütze

---

Links

DOI

---

Research Areas

 A3 | Computational Models

 B2 | Natural Language Processing

 C4 | Computational Social Sciences