{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/llamea-a-large-language-model-evolutionary","title":"LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics","arxiv_id":"2405.20132","date":"2024-05-30","proceeding":null,"authors":["Niki van Stein","Thomas Bäck"],"abstract":"Large Language Models (LLMs) such as GPT-4 have demonstrated their ability to understand natural language and generate complex code snippets. This paper introduces a novel Large Language Model Evolutionary Algorithm (LLaMEA) framework, leveraging GPT models for the automated generation and refinement of algorithms. Given a set of criteria and a task definition (the search space), LLaMEA iteratively generates, mutates and selects algorithms based on performance metrics and feedback from runtime evaluations. This framework offers a unique approach to generating optimized algorithms without requiring extensive prior expertise. We show how this framework can be used to generate novel black-box metaheuristic optimization algorithms automatically. LLaMEA generates multiple algorithms that outperform state-of-the-art optimization algorithms (Covariance Matrix Adaptation Evolution Strategy and Differential Evolution) on the five dimensional black box optimization benchmark (BBOB). The algorithms also show competitive performance on the 10- and 20-dimensional instances of the test functions, although they have not seen such instances during the automated generation process. The results demonstrate the feasibility of the framework and identify future directions for automated generation and optimization of algorithms via LLMs.","url_abs":"https://arxiv.org/abs/2405.20132v4","url_pdf":"https://arxiv.org/pdf/2405.20132v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"llamea-a-large-language-model-evolutionary","repo_url":"https://github.com/nikivanstein/LLaMEA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"llamea-a-large-language-model-evolutionary","repo_url":"https://github.com/XAI-liacs/BLADE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"metaheuristic-optimization","task_name":"Metaheuristic Optimization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"llamea","name":"LLaMEA","full_name":"algorithms and experiments from the paper"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.20132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20132"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XAI-liacs/BLADE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nikivanstein/LLaMEA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e8bee405414a2ff9","entry":"apply_code_delta","repo":"nikivanstein/LLaMEA","repo_kind":"official","path":"llamea/utils.py","file_url":"https://github.com/nikivanstein/LLaMEA/blob/HEAD/llamea/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8bee405414a2ff9"}},{"code_sha256_prefix":"e21fd9e6811ceba9","entry":"code_distance","repo":"nikivanstein/LLaMEA","repo_kind":"official","path":"llamea/utils.py","file_url":"https://github.com/nikivanstein/LLaMEA/blob/HEAD/llamea/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e21fd9e6811ceba9"}},{"code_sha256_prefix":"86de402f83009c18","entry":"discrete_power_law_distribution","repo":"nikivanstein/LLaMEA","repo_kind":"official","path":"llamea/utils.py","file_url":"https://github.com/nikivanstein/LLaMEA/blob/HEAD/llamea/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86de402f83009c18"}},{"code_sha256_prefix":"8cd2176033652f6c","entry":"average_nearest_neighbor_distance","repo":"XAI-liacs/BLADE","repo_kind":"listed","path":"iohblade/behaviour_metrics.py","file_url":"https://github.com/XAI-liacs/BLADE/blob/HEAD/iohblade/behaviour_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd2176033652f6c"}},{"code_sha256_prefix":"0685ce4ccba5952e","entry":"get_coordinates","repo":"XAI-liacs/BLADE","repo_kind":"listed","path":"iohblade/behaviour_metrics.py","file_url":"https://github.com/XAI-liacs/BLADE/blob/HEAD/iohblade/behaviour_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0685ce4ccba5952e"}},{"code_sha256_prefix":"5cfecc39564e3163","entry":"get_objective","repo":"XAI-liacs/BLADE","repo_kind":"listed","path":"iohblade/behaviour_metrics.py","file_url":"https://github.com/XAI-liacs/BLADE/blob/HEAD/iohblade/behaviour_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cfecc39564e3163"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}