LLM4AD: A Platform for Algorithm Design with Large Language Model
Not on the map. Why?
Abstract (arXiv)
We introduce LLM4AD, a unified Python platform for algorithm design (AD) with large language models (LLMs). LLM4AD is a generic framework with modularized blocks for search methods, algorithm design tasks, and LLM interface. The platform integrates numerous key methods and supports a wide range of algorithm design tasks across various domains including optimization, machine learning, and scientific discovery. We have also designed a unified evaluation sandbox to ensure a secure and robust assessment of algorithms. Additionally, we have compiled a comprehensive suite of support resources, including tutorials, examples, a user manual, online resources, and a dedicated graphical user interface (GUI) to enhance the usage of LLM4AD. We believe this platform will serve as a valuable tool for fostering future development in the merging research direction of LLM-assisted algorithm design.
Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 23 Dec 2024.
Builds on
17 of 27 references.
References · 17
- 2023GPT-4 Technical Reportcited by 18,396
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2024Qwen2 Technical Reportcited by 2,120
- 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
- 2024Yi: Open Foundation Models by 01.AIcited by 719
- 2024Automated Design of Agentic Systemscited by 407
- 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 276
- 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
- 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Modelscited by 246
- 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 133
- 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 69
- 2024Multi-objective Evolution of Heuristic Using Large Language Modelcited by 54
5 more
- 2024Evolving Code with A Large Language Modelcited by 43
- 2024Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Modelscited by 22
- 2024Large Language Models as Surrogate Models in Evolutionary Algorithms: A Preliminary Studycited by 20
- 2024Evolve Cost-aware Acquisition Functions Using Large Language Modelscited by 17
- 2024AutoTurb: Using Large Language Models for Automatic Algebraic Model Discovery of Turbulence Closurecited by 2
Built on by
Citing papers per year: 2025: 16; 2026: 17.
33 papers.
Sort:
By area:
- 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Designcited by 109
- 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 54
- 2025Large Language Models as End-to-end Combinatorial Optimization Solverscited by 28
- 2025Glia: A Human-Inspired AI for Automated Systems Design and Optimizationcited by 16
- 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearchcited by 15
- 2025Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learningcited by 12
- 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solvingcited by 11
- 2026Recursive self-improvement of AI research agentscited by 11
- 2025Fitness Landscape of Large Language Model-Assisted Automated Algorithm Searchcited by 9
- 2025Generalizable Heuristic Generation Through LLMs with Meta-Optimizationcited by 9
- 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 7
- 2025VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problemscited by 7
21 more
- 2025Fine-tuning Large Language Model for Automated Algorithm Designcited by 6
- 2025TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolutioncited by 5
- 2025Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Constructioncited by 5
- 2025Improving Existing Optimization Algorithms with LLMscited by 4
- 2026The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithmscited by 3
- 2026AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Designcited by 3
- 2025Let the Barbarians In: How AI Can Accelerate Systems Performance Researchcited by 2
- 2026EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Modelscited by 2
- 2026AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discoverycited by 2
- 2026ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentationcited by 1
- 2026BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Designcited by 1
- 2026Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Searchcited by 1
- 2026ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Searchcited by 1
- 2025From Performance to Understanding: A Vision for Explainable Automated Algorithm Designcited by 0
- 2026Constraint-aware Path Planning from Natural Language Instructions Using Large Language Modelscited by 0
- 2026CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discoverycited by 0
- 2026Latent Heuristic Search: Continuous Optimization for Automated Algorithm Designcited by 0
- 2026Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generationcited by 0
- 2026Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networkscited by 0
- 2026OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimizationcited by 0
- 2026Autoresearch in Mixed-Integer Linear and Nonlinear Programmingcited by 0
- 2026Autoresearch in Mixed-Integer Linear and Nonlinear Programming30 Sep 2026
- 2026OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization29 Sep 2026
- 2026Recursive self-improvement of AI research agents22 Sep 2026
- 2026AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery14 Sep 2026
- 2026ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search16 Aug 2026
- 2026Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search4 Aug 2026
- 2026Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks1 Jun 2026
- 2026Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation26 May 2026
- 2026Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design16 May 2026
- 2026EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models12 May 2026
- 2026AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design9 May 2026
- 2026BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design14 Apr 2026
21 more
- 2026The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms11 Apr 2026
- 2026ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation7 Apr 2026
- 2026CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery1 Apr 2026
- 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch25 Mar 2026
- 2026Constraint-aware Path Planning from Natural Language Instructions Using Large Language Models26 Feb 2026
- 2025Let the Barbarians In: How AI Can Accelerate Systems Performance Research16 Dec 2025
- 2025Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction26 Nov 2025
- 2025From Performance to Understanding: A Vision for Explainable Automated Algorithm Design20 Nov 2025
- 2025Glia: A Human-Inspired AI for Automated Systems Design and Optimization31 Oct 2025
- 2025VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems8 Oct 2025
- 2025Barbarians at the Gate: How AI is Upending Systems Research7 Oct 2025
- 2025Large Language Models as End-to-end Combinatorial Optimization Solvers21 Sep 2025
- 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving10 Sep 2025
- 2025Fine-tuning Large Language Model for Automated Algorithm Design13 Jul 2025
- 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings8 Jun 2025
- 2025Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning3 Jun 2025
- 2025Generalizable Heuristic Generation Through LLMs with Meta-Optimization27 May 2025
- 2025TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution7 May 2025
- 2025Fitness Landscape of Large Language Model-Assisted Automated Algorithm Search28 Apr 2025
- 2025Improving Existing Optimization Algorithms with LLMs12 Feb 2025
- 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design15 Jan 2025
- 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearchcited by 15
- 2026Recursive self-improvement of AI research agentscited by 11
- 2026The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithmscited by 3
- 2026AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Designcited by 3
- 2026AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discoverycited by 2
- 2026CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discoverycited by 0
- 2026Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generationcited by 0
- 2026Recursive self-improvement of AI research agents22 Sep 2026
- 2026AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery14 Sep 2026
- 2026Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation26 May 2026
- 2026AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design9 May 2026
- 2026The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms11 Apr 2026
- 2026CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery1 Apr 2026
- 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch25 Mar 2026
- 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 54
- 2025Large Language Models as End-to-end Combinatorial Optimization Solverscited by 28
- 2025Glia: A Human-Inspired AI for Automated Systems Design and Optimizationcited by 16
- 2025Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learningcited by 12
- 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solvingcited by 11
- 2025Fitness Landscape of Large Language Model-Assisted Automated Algorithm Searchcited by 9
- 2025Generalizable Heuristic Generation Through LLMs with Meta-Optimizationcited by 9
- 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 7
- 2025VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problemscited by 7
- 2025Fine-tuning Large Language Model for Automated Algorithm Designcited by 6
- 2025TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolutioncited by 5
- 2025Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Constructioncited by 5
12 most cited of 25 All 25 (JSON)
- 2026Autoresearch in Mixed-Integer Linear and Nonlinear Programming30 Sep 2026
- 2026OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization29 Sep 2026
- 2026ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search16 Aug 2026
- 2026Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search4 Aug 2026
- 2026Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks1 Jun 2026
- 2026Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design16 May 2026
- 2026EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models12 May 2026
- 2026BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design14 Apr 2026
- 2026ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation7 Apr 2026
- 2026Constraint-aware Path Planning from Natural Language Instructions Using Large Language Models26 Feb 2026
- 2025Let the Barbarians In: How AI Can Accelerate Systems Performance Research16 Dec 2025
- 2025Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction26 Nov 2025
12 newest of 25 All 25 (JSON)