Solving complex problems with large language models

• Event: Seminar
• Presented by: Alexander Koller from Saarland University
• Date: 30 April 2025
• Time: 13:15-15:00
• Venue: Gothenburg University, Humanisten and online
• Address: Renströmsgatan 6, 412 55 Göteborg
• Room: J411
• Zoom link: https://gu-se.zoom.us/j/69780476534?pwd=Q9Uw2lu0zda8MsXkL08eGrqU64DMpp.1

Abstract

One of the great promises that people connect with LLMs is that they can make complex problem-solving with computers accessible to lay users. Unlike optimal solvers (e.g. for planning or linear programming), LLMs accept natural-language input and require no expert training; unlike earlier task-oriented dialogue systems, they can be applied across arbitrary domains.

In my talk, I will explore the degree to which LLMs are already fulfilling this promise. I will present recent work on whether current LLMs “reason or recite” when solving NP-hard optimization problems and ongoing research on building dialogue agents that play two-player optimization games. I will conclude with some thoughts on future avenues of research.