{"id":13484313,"url":"https://github.com/google-deepmind/funsearch","last_synced_at":"2025-06-17T00:39:58.758Z","repository":{"id":212525400,"uuid":"722545811","full_name":"google-deepmind/funsearch","owner":"google-deepmind","description":null,"archived":false,"fork":false,"pushed_at":"2024-02-05T10:32:18.000Z","size":1080,"stargazers_count":800,"open_issues_count":5,"forks_count":148,"subscribers_count":20,"default_branch":"main","last_synced_at":"2025-03-27T16:40:17.245Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/google-deepmind.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-23T11:33:50.000Z","updated_at":"2025-03-24T11:28:39.000Z","dependencies_parsed_at":"2024-02-05T11:57:44.170Z","dependency_job_id":null,"html_url":"https://github.com/google-deepmind/funsearch","commit_stats":null,"previous_names":["google-deepmind/funsearch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/google-deepmind/funsearch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Ffunsearch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Ffunsearch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Ffunsearch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Ffunsearch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/google-deepmind","download_url":"https://codeload.github.com/google-deepmind/funsearch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google-deepmind%2Ffunsearch/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260268635,"owners_count":22983601,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T17:01:22.341Z","updated_at":"2025-06-17T00:39:58.736Z","avatar_url":"https://github.com/google-deepmind.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","🤖 Research Agents \u0026 Autonomous Workflows"],"sub_categories":["Autonomous Research Systems (2023-2025 Breakthroughs)"],"readme":"# FunSearch\n\nThis repository accompanies the publication\n\n\u003e Romera-Paredes, B. et al. [Mathematical discoveries from program search with large language models](https://www.nature.com/articles/s41586-023-06924-6). *Nature* (2023)\n\nThere are 6 independent directories:\n\n- `cap_set` contains functions discovered by FunSearch that construct large cap\nsets, and we also provide those cap sets in a numerical format for convenience.\n\n- `admissible_set` contains functions discovered by FunSearch that construct\nlarge admissible sets, and we also provide those admissible sets in a numerical\nformat for convenience.\n\n- `bin_packing` contains heuristics discovered by FunSearch for online 1D bin\npacking problems, and an evaluation suite to reproduce the results reported in\nthe paper.\n\n- `cyclic_graphs` contains functions discovered by FunSearch that construct\nlarge independent sets in strong products of cyclic graphs, and we also provide\nthose sets in a numerical format for convenience.\n\n- `corner_free_sets` contains the discovered sets of indices, in numerical\nformat, satisfying the combinatorial degeneration constraints described for the\ncorners-free problem in the Supplementary Information.\n\n- `implementation` contains an implementation of the evolutionary algorithm,\ncode manipulation routines, and a single-threaded implementation of the\nFunSearch pipeline. It does not contain language models for generating new\nprograms, the sandbox for executing untrusted code, nor the infrastructure for\nrunning FunSearch on our distributed system. This directory is intended to be\nuseful for understanding the details of our method, and for adapting it for use\nwith any available language models, sandboxes, and distributed systems.\n\n## Installation\n\nNo installation is required. All notebooks can be opened and run in Google\nColab.\n\n## Usage\n\n- `cap_set`: The notebook `cap_set.ipynb` can be opened via\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/funsearch/blob/master/cap_set/cap_set.ipynb).\n\n- `admissible_set`: The notebook `admissible_set.ipynb` can be opened\nvia\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/funsearch/blob/master/admissible_set/admissible_set.ipynb).\n\n- `bin_packing`: The notebook `bin_packing.ipynb` can be opened via\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/funsearch/blob/master/bin_packing/bin_packing.ipynb).\n\n- `cyclic_graphs`: The notebook `cyclic_graphs.ipynb` can be opened via\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-deepmind/funsearch/blob/master/cyclic_graphs/cyclic_graphs.ipynb).\n\n## Citing this work\n\nIf you use the code or data in this package, please cite:\n\n```bibtex\n@Article{FunSearch2023,\n  author  = {Romera-Paredes, Bernardino and Barekatain, Mohammadamin and Novikov, Alexander and Balog, Matej and Kumar, M. Pawan and Dupont, Emilien and Ruiz, Francisco J. R. and Ellenberg, Jordan and Wang, Pengming and Fawzi, Omar and Kohli, Pushmeet and Fawzi, Alhussein},\n  journal = {Nature},\n  title   = {Mathematical discoveries from program search with large language models},\n  year    = {2023},\n  doi     = {10.1038/s41586-023-06924-6}\n}\n```\n\n## License and disclaimer\n\nCopyright 2023 DeepMind Technologies Limited\n\nAll software is licensed under the Apache License, Version 2.0 (Apache 2.0);\nyou may not use this file except in compliance with the Apache 2.0 license.\nYou may obtain a copy of the Apache 2.0 license at:\nhttps://www.apache.org/licenses/LICENSE-2.0\n\nAll other materials are licensed under the Creative Commons Attribution 4.0\nInternational License (CC-BY). You may obtain a copy of the CC-BY license at:\nhttps://creativecommons.org/licenses/by/4.0/legalcode\n\nUnless required by applicable law or agreed to in writing, all software and\nmaterials distributed here under the Apache 2.0 or CC-BY licenses are\ndistributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,\neither express or implied. See the licenses for the specific language governing\npermissions and limitations under those licenses.\n\nThis is not an official Google product.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle-deepmind%2Ffunsearch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoogle-deepmind%2Ffunsearch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle-deepmind%2Ffunsearch/lists"}