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

181 papers15 papers in the last four weeks, down 58% on the four weeks before. 0.1% of all new papers.

  1. Speeding up Automated Algorithm Design by Batch Evaluation: A Case Study of Genetic Programming for Ant Colony Optimisation

    Nov 15, 2026Bo-Cheng Lin, Yi Mei, Mengjie ZhangGPU AccelerationAutomated Algorithm Discovery

  2. Agentic Computational Algebra

    Nov 11, 2026Ryan A. Anderson, Matthew Trager, Ben Bowman +2Algorithmic ReasoningAutomated Algorithm Discovery

  3. AutoAssumption: Searching over Assumptions Discovers ML-Systems Algorithms

    Nov 10, 2026Igor Sadalski, Minghao Guo, Benjamin Jones +1Automated Algorithm DiscoveryKV-Cache Eviction

  4. Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

    Nov 10, 2026Wenji Fang, Yao Lu, Jinghua Wang +1Electronic Design AutomationSelf-Improving Agents

  5. AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding

    Nov 10, 2026Burak Susam, Ruiyuan Kang, Tingting MuData VisualizationAutomated Algorithm Discovery

  6. Autonomous Optimization of Numerical Algorithms by an AI Agent: Application to Atomistic Simulation

    Nov 9, 2026Jeheon WooAutomated Algorithm DiscoveryAI Coding Agents

  7. Discovering formally verified quantum programs with AI

    Nov 6, 2026Sergey Shirobokov, Ben Jaderberg, Katerina Hristova +22Automated Algorithm DiscoveryProgram Synthesis

  8. EnzymeRSI: A dual-loop recursive self-improvement system for enzyme design

    Nov 4, 2026Genoria AI Team, Yuejie Hou, Lixiang Yang +4Recursive Self-ImprovementProtein Design

  9. RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms

    Nov 2, 2026Tingran Gan, Zhouziyue Lu, Dian Jin +7Recommender SystemsAutomated Algorithm Discovery

  10. Dream-COP: Guiding Algorithm Discovery for Combinatorial Optimization Problems in an Experience World

    Oct 27, 2026Kuan Xu, Jianming Wang, Ni Zhang +3Automated Algorithm DiscoveryCombinatorial Optimization

  11. Coral Discovery: The Division of Cognitive Labor in Autonomous Research

    Oct 23, 2026Xinxing Ren, Qianbo Zang, Ziyan Wang +9Autonomous Research AgentsMulti-Agent Coordination

  12. SplatLab: Autonomous Scientific Discovery for 3DGS Research

    Oct 21, 2026Seemandhar Jain, Manmohan ChandrakerAutonomous Research AgentsAutomated Algorithm Discovery

  13. SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery

    Oct 20, 2026Ha Minh Hieu, Tongyao Zhu, Do Xuan Long +1Large Language Model-Guided Scientific DiscoveryLLMs for Evolutionary Optimization

  14. Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research

    Oct 18, 2026Yue Huang, Zhangchen Xu, Xiaonan Luo +16Operations ResearchAutonomous Research Agents

  15. Scaling Discovery Requires Forgetting

    Oct 14, 2026Shangyin Tan, Ben Zhou, Lakshya A Agrawal +8AI Agents for Scientific DiscoveryLLM Agent Memory

  16. HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery

    Oct 12, 2026Yingzi Ma, Yulong Cao, Nanxi Li +5Agent Harness OptimizationLLM Agent Harnesses

  17. EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research

    Oct 12, 2026Haolin Yang, Zhiqiang Qian, Chutian Chen +7Alpha Factor DiscoveryQuantitative Finance

  18. AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems

    Oct 12, 2026Eugenio Cainelli, Lorenzo Luccioli, Alessandro Iraci +1Automated Algorithm DiscoveryLarge Language Model-Guided Scientific Discovery

  19. AutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms

    Oct 12, 2026Joel Shor, Subhashini VenugopalanMolecule DesignMolecular Generation

  20. AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning

    Oct 11, 2026Peiqi Jiang, Fan Zhang, Xin Xu +2Alpha Factor DiscoveryQuantitative Finance

  21. Generative Adversarial Loops

    Oct 8, 2026Kislay Aditya Oj, Nidhi Jain, Sri Surya Varma Datla +3Automated Algorithm DiscoveryGenerative Adversarial Networks

  22. Kernel Autoresearch for Open-Ended Model Discovery

    Oct 7, 2026Richard Cornelius Suwandi, Feng Yin, Kevin MurphyKernel MethodsAutomated Algorithm Discovery

  23. When Algorithmic Exploration Becomes Cheap: A Case Study of Agentic Research in EDA

    Oct 7, 2026Keren Zhu, Yu Deng, Xiaoyu Hao +6AI-Assisted Scientific ResearchAutonomous Research Agents

  24. RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms

    Oct 6, 2026Haoran Li, Zengle Ge, Xiaomin Yuan +14Automated Algorithm DiscoveryEvolutionary RL