paper-with-me

홈 › Papers

DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning

2026-03-18 · Alexander D. Goldie, Zilin Wang, Adrian Hayler, Deepak Nathani, Edan Toledo, Ken Thampiratwong, Aleksandra Kalisz, Michael Beukman, Hannah Erlebach, Alistair Letcher, Shashank Reddy, Clarisse Wibault, Theo Wolf, Charles O'Neill, Uljad Berdica, Nicholas Roberts, Saeed Rahmani, Roberta Raileanu, Shimon Whiteson, Jakob N. Foerster arxiv

Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems has thus far been limited by existing task suites. They suffer from many issues, such as: poor evaluation methodologies; data contamination; and containing saturated or very similar problems. Here, we introduce DiscoGen, a procedural generator of algorithm discovery tasks for machine learning, such as developing optimisers for reinforcement learning or loss functions for image classification. Motivated by the success of procedural generation in reinforcement learning, DiscoGen spans billions of tasks of varying difficulty and complexity from a range of machine learning fields. These tasks are specified by a small number of configuration parameters and can be used to optimise algorithm discovery agents (ADAs). We present DiscoBench, a fixed, small subset of DiscoGen tasks for principled evaluation of ADAs. Finally, we propose a number of ambitious, impactful research directions enabled by DiscoGen, and demonstrate its use for ADA optimisation through scaling experiments for automated prompt tuning. DiscoGen is released open-source at https://github.com/AlexGoldie/discogen.

📄 PDF Abstract BibTeX arXiv:2603.17863

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningImage Classification

Similar Papers 제목 키워드 기반

DiscoGen: Learning to Discover Gene Regulatory Networks

2023-04-12 · Nan Rosemary Ke, Sara-Jane Dunn, Jorg Bornschein, Silvia Chiappa 외

Accurately inferring Gene Regulatory Networks (GRNs) is a critical and challenging task in biology. GRNs model the activatory and inhibitory interactions between genes and are inherently causal in nature. To accurately i…

Causal Discovery

Procedural Content Metageneration via Program Search and Continual Abstraction Discovery

2026-08-18 · Matthew Siper, Ahmed Khalifa, Julian Togelius arxiv

Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We study this approach in Sokoban, Zelda, Dangerous Dav…

Learning to Generate Levels From Nothing

2020-02-12 · Philip Bontrager, Julian Togelius

Machine learning for procedural content generation has recently become an active area of research. Levels vary in both form and function and are mostly unrelated to each other across games. This has made it difficult to …

Image GenerationInductive LearningReinforcement Learning

Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A

2024-09-02 · K Roth, Rushil Gupta, Simon Halle, Bang Liu

Large language models struggle to synthesize disparate pieces of information into a coherent plan when approaching a complex procedural task. In this work, we introduce a novel formalism and structure for such procedural…

Language ModellingQuestion AnsweringRAG

Guided Proceduralization: Optimizing Geometry Processing and Grammar Extraction for Architectural Models

2018-07-06 · Ilke Demir, Daniel G. Aliaga

We describe a guided proceduralization framework that optimizes geometry processing on architectural input models to extract target grammars. We aim to provide efficient artistic workflows by creating procedural represen…