Automated Algorithm Discovery

Overview

Automated algorithm discovery studies how to construct or improve executable procedures—such as heuristics, numerical solvers, learning rules, and hardware policies—without specifying every design choice by hand. Common approaches use evolutionary or tree search with language models to modify code, program synthesis over reusable components, reinforcement learning, or learned search controllers; candidates are assessed with benchmarks, simulators, formal checks, and staged evaluation. Persistent memory, modular representations, diversity archives, and adaptive budget allocation help reuse findings and reduce search stagnation. A central challenge is establishing that gains reflect sound, useful algorithms rather than benchmark overfitting, noisy evaluations, recombinations of human designs, or exploitable evaluators—and that they transfer under real-world constraints.

Latest papers

CardsList

170 papers33 papers in the last four weeks, up 120% on the four weeks before. 0.2% of all new papers.

  1. Automated Grammar-based Algebraic Multigrid Design With Evolutionary Algorithms

    Mar 18, 2026Dinesh Parthasarathy, Wayne Mitchell, Arjun Gambhir +2Automated Algorithm Discovery

  2. Reinforced Generation of Combinatorial Structures: Ramsey Numbers

    Mar 10, 2026Ansh Nagda, Prabhakar Raghavan, Abhradeep ThakurtaAutomated Algorithm Discovery

  3. Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs

    Mar 9, 2026Chen Lu, Ke Xue, Chengrui Gao +5Automated Algorithm DiscoveryAutomated Heuristic Design

  4. CDEoH: Category-Driven Automatic Algorithm Design With Large Language Models

    Mar 8, 2026Yu-Nian Wang, Shen-Huan Lyu, Ning Chen +3Automated Heuristic DesignAutomated Algorithm Discovery

  5. Autonomous Algorithm Discovery for Ptychography via Evolutionary LLM Reasoning

    Mar 5, 2026Xiangyu Yin, Ming Du, Junjing Deng +3Image ReconstructionAutomated Algorithm Discovery

  6. Solving an Open Problem in Theoretical Physics using AI-Assisted Discovery

    Mar 5, 2026Michael P. Brenner, Vincent Cohen-Addad, David WoodruffLarge Language Model-Guided Scientific DiscoveryAutomated Algorithm Discovery

  7. From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors

    Mar 3, 2026Qi Huang, Furong Ye, Ananta Shahane +2Large Language Model-Guided OptimizationAutomated Algorithm Discovery

  8. Rethinking Code Similarity for Automated Algorithm Design with LLMs

    Mar 3, 2026Rui Zhang, Zhichao LuAutomated Algorithm Discovery

  9. EvoX: Meta-Evolution for Automated Discovery

    Feb 26, 2026Shu Liu, Shubham Agarwal, Monishwaran Maheswaran +14Evolutionary OptimizationLLMs for Evolutionary Optimization

  10. ArchAgent: Agentic AI-driven Computer Architecture Discovery

    Feb 25, 2026Raghav Gupta, Akanksha Jain, Abraham Gonzalez +10Automated Algorithm DiscoveryAI Agents for Scientific Discovery

  11. AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing

    Feb 19, 2026Jianda Du, Youran Sun, Haizhao YangPDE SolvingAutomated Algorithm Discovery

  12. RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution

    Feb 18, 2026Jinming Nian, Fangchen Li, Dae Hoon Park +1Information RetrievalAutomated Algorithm Discovery

  13. Simple Baselines are Competitive with Code Evolution

    Feb 18, 2026Yonatan Gideoni, Sebastian Risi, Yarin GalLLMs for Evolutionary OptimizationCode Generation Evaluation

  14. MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models

    Feb 17, 2026Tianyi Li, Shihui Zang, Moritz MünchmeyerAutomated Algorithm DiscoveryScientific Code Generation

  15. FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discovery

    Feb 16, 2026Yanlong Wang, Jian Xu, Hongkang Zhang +3Alpha Factor DiscoveryAlgorithmic Trading

  16. ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search

    Feb 10, 2026Alexey Kravatskiy, Valentin Khrulkov, Ivan OseledetsLarge Language Model-Guided Scientific DiscoveryEvolutionary Optimization

  17. Learning to Discover Iterative Spectral Algorithms

    Feb 10, 2026Zihang Liu, Oleg Balabanov, Yaoqing Yang +1Automated Algorithm DiscoveryLearning to Optimize