Problem Solving Through Human-AI Preference-Based Cooperation
This addresses the problem of unreliable AI partners in expert domains for researchers and practitioners, but it is incremental as it focuses on early formalization and discussion rather than implementation or results.
The paper tackles the challenge of AI's inability to reliably cooperate with humans on complex expert problems by proposing HAICo2, a novel human-AI co-construction framework, and takes initial steps toward formalizing it while identifying open research issues.
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.