Large Language Models | Intelligent Optimization Lab

Large Language Models for Optimization

Sat, 26 Sep 2026 00:00:00 +0000

IOLab investigates how large language models can complement established combinatorial optimization techniques. Rather than treating an LLM as a stand-alone solver, we study its role as one component of a structured optimization system.

Our work examines LLM-based generative operators within metaheuristics, the ability of models to recall and interpret problem features, and the information encoded in their internal representations. These representations can be evaluated as surrogates for predicting instance difficulty and algorithm behavior in algorithm-selection scenarios.

The group has published a systematic review of LLMs for combinatorial optimization and experimental work on feature extraction and algorithm selection.

Francesca Da Ros Wins the 2026 AIROYoung Dissertation Award

Thu, 10 Sep 2026 00:00:00 +0000

IOLab congratulates Francesca Da Ros on winning the 2026 AIROYoung Dissertation Award with her thesis, Chronicles on Metaheuristic Optimization: Components, Applications, and Large Language Models. The award ceremony took place on 10 September 2026 during the national ODS conference in Galzignano Terme, Italy.

The AIROYoung Dissertation Award is presented by the Italian Operations Research Society to the best doctoral dissertation in Decision Sciences defended at an Italian university during the relevant period. The selection process evaluates both the dissertation and its related scientific publications and concludes with a presentation by the finalists at the ODS conference.

Francesca Da Ros at the AIROYoung Dissertation Award ceremony during ODS 2026.

Francesca’s research investigates advanced optimization techniques for complex decision-making, with a strong focus on real-world applications. One case study addresses the scheduling of production cycles for industrial furnaces, seeking to improve production efficiency while reducing energy consumption and making the process more sustainable.

A second application concerns home healthcare planning. Optimization methods are used to organize caregivers’ visits and activities while considering not only service efficiency, but also individual patient needs and the personalization of care.

Alongside these applications, the dissertation examines how the behavior of optimization algorithms can be better understood and compared. It also investigates how generative artificial intelligence systems, particularly large language models, can support optimization processes.

Large Language Models for Combinatorial Optimization: A Systematic Review

Wed, 01 Apr 2026 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Behavior and representation in open-weight Large Language Models for combinatorial optimization: From feature extraction to algorithm selection

Thu, 01 Jan 2026 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.