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

PACE: Primitive-Aware Code Evolution for Automated Algorithm Design
Aug 7, 2026Zhuoliang Xie, Ruihao Zheng, Xiang Xu +2Automated Algorithm Discovery Automated Heuristic Design
1Southern University of Science and Technology · 2Shenzhen University
An AI4AI Framework for Visual Token Pruning
Aug 7, 2026Zhen Liu, Wenli Huang, Wei Song +3Automated Algorithm Discovery Efficient VLM Inference
Xi’an Jiaotong University · Ningbo University of Technology · 3North China University of Technology +3
Autonomous discovery of accelerator commissioning algorithms
Aug 7, 2026Thorsten HellertAutomated Algorithm Discovery Large Language Model-Guided Scientific Discovery
Lawrence Berkeley National Laboratory · Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative Investment
Aug 5, 2026Zongqian Li, Yaoyiran Li, Yaohui Guo +3Automated Algorithm Discovery Autonomous Research Agents
1Google · University of Cambridge
AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search
Aug 4, 2026Weicheng Ye, Youran Sun, Xingyu Ren +3Quantitative Finance Automated Algorithm Discovery
Department of Physics, The Chinese University of Hong Kong, Hong Kong SAR, China · Department of Mathematics, University of Maryland, College Park, MD, USA · Department of Computer Science, University of Maryland, College Park, MD, USA
AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery
Aug 4, 2026Zhijing Hu, Changjun Fan, Yufan Deng +1Automated Algorithm Discovery Automated Heuristic Design
College of Systems Engineering, National University of Defense Technology Changsha, China · School of Computing and Information Systems, Singapore Management University Singapore
Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search
Aug 4, 2026Qinglong Hu, Qingfu Zhang, Fei Liu +3Algorithm Selection Automated Algorithm Discovery
Department of Computer Science, City University of Hong Kong, Hong Kong, China · Huawei Noah’s Ark Lab, China
Towards Autonomous Formulaic Alpha Discovery: An Evolutionary Computation Perspective
Aug 3, 2026Xinwei Yu, Yiyang Fu, Mingcheng Fan +3Automated Algorithm Discovery Evolutionary Optimization
Xi’an Jiaotong-Liverpool University, Suzhou 215123, China · Shanghai University, Shanghai 200444, China
DGA $_2$ D: Directed Graph-Guided Automated Algorithm Design with Large Language Models
Aug 1, 2026Jiale Zhao, Zimu Chen, Sirui Mao +3Automated Algorithm Discovery Automated Heuristic Design
School of Automation Science and Electrical Engineering, Beihang University, Beijing, China · School of Computer Science and Engineering, Beihang University, Beijing, China
AutoPref: Automatic Discovery of Task-Specific Preference Objectives for Neural Combinatorial Optimization
Jul 30, 2026Shengda Gu, Kai Li, Xinyi Ke +3Automated Algorithm Discovery Pairwise Preference Evaluation
C2DL, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Tencent AI Lab +1
Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility
Jul 29, 2026Yansen Zhang, Yilu Liu, Tianyu Liu +6Inference-Time Search Automated Algorithm Discovery
International Digital Economy Academy (IDEA) · City University of Hong Kong · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining
Jul 29, 2026Jingyang Yi, Jian Yang, Yifei Jin +2Automated Algorithm Discovery Large Language Model-Guided Optimization
1X-Tech · 2Xtech-PandaAI-Waton Joint Lab · 3Monash University +2
EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
Jul 29, 2026Peng Yin, Kai Li, Yifan Zhang +1Automated Algorithm Discovery LLM-Based Program Synthesis
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China
AutoPSO: A Metaframework for Automated Particle Swarm Optimization
Jul 29, 2026Xinmeng Yu, Jiaxin Gao, Jianguo Zhang +2Automated Algorithm Discovery Automated Heuristic Design
Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China · Pengcheng Laboratory, Shenzhen 518000, China · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China +2
Recycling computational processes of dynamic programming for combinatorial optimization problems: a reservoir computing approach
Jul 25, 2026Sora Todaka, Akihiro Yamamoto, Nozomi AkashiAutomated Algorithm Discovery Dynamic Programming
Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan. · Institute for Liberal Arts and Sciences, Kyoto University, Sakyo-ku, Kyoto, Japan.
Machine Can Automatically Discover Parametric Functions to Model HEP Data
Jul 22, 2026Ho Fung Tsoi, Dylan Rankin, Cecile Caillol +5Automated Algorithm Discovery High-Energy Physics
University of Pennsylvania, USA · European Organization for Nuclear Research (CERN), Switzerland · University of Cambridge, UK +4
AutoIndex: Learning Representation Programs for Retrieval
Jul 21, 2026Sam O'Nuallain, Nithya Rajkumar, Ramya Narayanasamy +3Automated Algorithm Discovery Program Synthesis
University of Massachusetts Amherst · Databricks Mosaic Research
Automated Discovery Has No Universally Superior Harness
Jul 20, 2026Akshat Gupta, Jermaine Lei, Alexander Lu +2Automated Algorithm Discovery Automated Heuristic Design
UC Berkeley · MIT, MIT-IBM Watson AI Lab
Autonomous Discovery of Wireless Communications Algorithms
Jul 20, 2026Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer +4Automated Algorithm Discovery Large Language Model-Guided Optimization
NVIDIA, 92400 Courbevoie, France · NVIDIA, 10623 Berlin, Germany · NVIDIA, 8004 Zürich, Switzerland
Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer
Jul 19, 2026Jingjie Ning, Xiaochuan Li, Shanshan Zhong +2Automated Algorithm Discovery Automated Evaluation
School of Computer Science, Carnegie Mellon University · 2DP Technology
Program-Synthesis-Driven Autodesign of Universal Unitary Operators
Jul 11, 2026Yifei Zhang, Dong Chen, Fan Wang +6Automated Algorithm Discovery Program Synthesis
Key Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, China · Huawei Technologies Co., Ltd, Beijing 100095, China · Department of Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology, HongKong, China +6
XALPHA: A Memory-Driven AI Quant Researcher for Hypothesis-to-Code Alpha Discovery
Jul 9, 2026Fengyuan Liu, Yuchen Fu, Yuqi Wang +1Automated Algorithm Discovery Memory-Augmented Agents
School of Computing and Data Science, The University of Hong Kong · Grace Investment Machine
LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms
Jul 6, 2026Georgios Laskaris, Reuben Brasher, Niki van Stein +3Automated Algorithm Discovery Evolutionary Optimization
Terra Quantum AG, Kornhausstrasse 25, 9000 St. Gallen, Switzerland · LIACS, Leiden University, Leiden, Netherlands
QDEvo: A Multi-Objective Quality-Diversity Framework for Automated Heuristic Design
Jul 6, 2026Nam Do Khanh, Nhat Nguyen Tran Minh, Dat Pham Vu Tuan +2Automated Algorithm Discovery Automated Heuristic Design
Hanoi University of Science and Technology Hanoi, Vietnam · George Mason University Fairfax, Virginia, USA
SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery
Jul 2, 2026Yuvraj Virk, Zack Edds, Chunqiu Steven Xia +1Automated Algorithm Discovery Large Language Model-Guided Optimization
University of Illinois Urbana-Champaign
Auto-FL-Research: Agentic Search for Federated Learning Algorithms
Jul 1, 2026Holger R. Roth, Ziyue Xu, Chester Chen +3Automated Algorithm Discovery Autonomous Research Agents
NVIDIA, Santa Clara, USA
RAISE: LLM-based Automated Heuristic Design with Robust Adversary Instance Search
Jun 30, 2026Fei Liu, Alessio Figalli, Patrick Owen +1Distribution Shift Robustness Automated Algorithm Discovery
University of Zurich · 2ETH Zurich
AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills
Jun 29, 2026Xinyuan Song, Zekun Cai, Liang ZhaoAutomated Algorithm Discovery LLM-Based Program Synthesis
Emory University, Atlanta, GA, USA · The University of Tokyo, Tokyo, Japan · LocationMind, Tokyo, Japan
Semantics-Aware Bilevel Co-Evolution: Towards Automated Multicomponent Algorithm Design
Jun 29, 2026Zhiyao Zhang, Shenghao Wu, Xingyu Wu +1Automated Algorithm Discovery Evolutionary Optimization
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR 999077, China · College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution
Jun 28, 2026Yuqi Li, Siyuan Liu, Bingjun LiuAutomated Algorithm Discovery Multi-Agent Reasoning
Panda AI

Aug 7, 2026, cs.SEJ/K move · Enter open · S save

PACE: Primitive-Aware Code Evolution for Automated Algorithm Design

Zhuoliang Xie, Ruihao Zheng, Xiang Xu, Genghui Li+1

1Southern University of Science and Technology · 2Shenzhen University

Automated Algorithm Discovery Automated Heuristic Design Large Language Model-Guided Optimization LLM-Based Program Synthesis

Open paper AskPDF arXiv

Large Language Model (LLM)-based automated algorithm design typically evolves algorithms as complete, indivisible programs. While this whole-program perspective simplifies the search space, it fundamentally couples the useful local logic to its host program. Consequently, valuable code snippets vanish when the overall program is discarded, making it highly difficult to assess the contribution of individual algorithmic components.To address this, we propose Primitive-Aware Code Evolution (PACE), which decouples local logic from complete programs by representing it as persistent units called Executable Algorithmic Primitives (EAPs). To enable code-level transfer, PACE maintains a dynamic set of EAPs. Algorithm evolution is driven by primitive-aware operators that structurally guarantee the retention and cross-program transfer of these components. To evaluate them effectively, PACE leverages Thompson sampling based on parent-relative performance improvements, guiding primitive selection from the set without requiring extra evaluation datasets. Experiments on four tasks demonstrate that PACE effectively discovers competitive algorithms while structurally preserving valuable algorithmic components.

Momentum

Related topics

Latest papers 94