Automated Algorithm Discovery

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 94

All topics

EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs
Apr 17, 2026David BerghausEvent Time Prediction Time Series Imputation
Lamarr Institute · Fraunhofer IAIS
DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning
Mar 18, 2026Alexander D. Goldie, Zilin Wang, Adrian Hayler +17Automated Algorithm Discovery Synthetic Benchmark Generation
University of Oxford · University of California, Santa Barbara · University College London +1
ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search
Feb 10, 2026Alexey Kravatskiy, Valentin Khrulkov, Ivan OseledetsAutomated Algorithm Discovery Evolutionary Optimization
1MIRIAI, Russia · 2FusionBrain Lab, Russia · 3AXXX, Russia +1
Learning to Discover Iterative Spectral Algorithms
Feb 10, 2026Zihang Liu, Oleg Balabanov, Yaoqing Yang +1Automated Algorithm Discovery Learning to Optimize
1International Computer Science Institute · University of California, Berkeley · 4Lawrence Berkeley National Laboratory +1

Apr 17, 2026, cs.LGJ/K move · Enter open · S save

EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs

David Berghaus

Lamarr Institute · Fraunhofer IAIS

Event Time Prediction Time Series Imputation Automated Algorithm Discovery Interpretable ML LLM-Based Program Synthesis

Open paper AskPDF arXiv

We introduce EVIL (\textbf{EV}olving \textbf{I}nterpretable algorithms with \textbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover simple, interpretable algorithms for dynamical systems inference. Rather than training neural networks on large datasets, EVIL evolves pure Python/NumPy programs that perform zero-shot, in-context inference across datasets. We apply EVIL to three distinct tasks: next-event prediction in temporal point processes, rate matrix estimation for Markov jump processes, and time series imputation. In each case, a single evolved algorithm generalizes across all evaluation datasets without per-dataset training (analogous to an amortized inference model). To the best of our knowledge, this is the first work to show that LLM-guided program evolution can discover a single compact inference function for these dynamical-systems problems. Across the three domains, the discovered algorithms are often competitive with, and even outperform, state-of-the-art deep learning models while being orders of magnitudes faster, and remaining fully interpretable.

Momentum

Related topics

Latest papers 94

EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs

DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning

ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search

Learning to Discover Iterative Spectral Algorithms