activity
20242026
most citedPruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring

2 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

8 papers · 1 filter

cs.AI2026

LLaMEA-SAGE: Guiding Automated Algorithm Design with Structural Feedback from Explainable AI

Niki van Stein, Anna V. Kononova, Lars Kotthoff +1

Large language models have enabled automated algorithm design (AAD) by generating optimization algorithms directly from natural-language prompts. While evolutionary frameworks such…

cs.AI2026

LLM Driven Design of Continuous Optimization Problems with Controllable High-level Properties

Urban Skvorc, Niki van Stein, Moritz Seiler +3

Benchmarking in continuous black-box optimisation is hindered by the limited structural diversity of existing test suites such as BBOB. We explore whether large language models emb…

cs.AI2025

Agentic Large Language Models, a survey

Aske Plaat, Max van Duijn, Niki van Stein +3

Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research ag…

cs.AI2025

From Performance to Understanding: A Vision for Explainable Automated Algorithm Design

Niki van Stein, Anna V. Kononova, Thomas Bäck

Automated algorithm design is entering a new phase: Large Language Models can now generate full optimisation (meta)heuristics, explore vast design spaces and adapt through iterativ…

cs.AI2025

Multi-Step Reasoning with Large Language Models, a Survey

Aske Plaat, Annie Wong, Suzan Verberne +3

Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for.…

cs.AI2025

Reasoning Capabilities of Large Language Models on Dynamic Tasks

Annie Wong, Thomas Bäck, Aske Plaat +2

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-re…