Elamur Research
☰
home / papers / 2025 / AlphaEvolve: A coding agent for scientific and algorithmic discovery

AlphaEvolve: A coding agent for scientific and algorithmic discovery

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-ND 4.0 (arXiv)" does not allow redistributing the text itself. Original — arxiv.org/pdf/2506.13131

Summary

AlphaEvolve is a coding agent from Google DeepMind. It tests whether large language models can produce new discoveries, not just strong benchmark scores, on problems where a machine can check candidate answers. The user supplies three things: a working starting program with sections flagged for evolution, an evaluation function that returns numerical scores, and optional background context. An evolutionary loop then picks parent programs from a database and builds prompts from earlier attempts. An ensemble of state-of-the-art LLMs proposes code diffs, and the resulting programs are scored and stored for later rounds. AlphaEvolve builds on the earlier FunSearch system but covers much more. It can rewrite whole files in any language, optimize several metrics together and run evaluations that take hours. It found better algorithms in mathematics, in matrix multiplication and in parts of Google's own computing infrastructure. The main limitation is that every task needs an automated evaluator, so experimental sciences remain largely out of reach for now.

Key points

  • AlphaEvolve found a way to multiply two 4×4 complex-valued matrices with 48 scalar multiplications. This is the first improvement in this setting in 56 years over Strassen's 1969 algorithm, and the system improved the state of the art for 14 matrix multiplication targets in total.
  • The team tested it on more than 50 open mathematical construction problems. It matched the best known result on about 75% and beat it on about 20%, including Erdős's Minimum Overlap Problem and the kissing number in 11 dimensions.
  • Inside Google it found:
    • a better scheduling heuristic for data centers
    • a simpler but functionally equivalent arithmetic circuit for TPUs
    • faster matrix-multiplication kernels, which sped up training of the LLM that AlphaEvolve itself runs on
  • Compared with FunSearch, AlphaEvolve evolves hundreds of lines instead of a single function. It needs thousands of LLM samples rather than millions and benefits from stronger models.
  • The discovered algorithms and mathematical results are published in a Google Colab notebook in the google-deepmind/alphaevolve_results repository.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Computing & GPUs

Cited by

162 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 161 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2506.13131 · arXiv 2506.13131

@misc{novikov2025alphaevolve,
  title = {{AlphaEvolve: A coding agent for scientific and algorithmic discovery}},
  author = {Novikov, Alexander and Vũ, Ngân and Eisenberger, Marvin and Dupont, Emilien and Huang, Po-Sen and Wagner, Adam Zsolt and Shirobokov, Sergey and Kozlovskii, Borislav and Ruiz, Francisco J. R. and Mehrabian, Abbas and Kumar, M. Pawan and See, Abigail and Chaudhuri, Swarat and Holland, George and Davies, Alex and Nowozin, Sebastian and Kohli, Pushmeet and Balog, Matej},
  year = {2025},
  doi = {10.48550/arxiv.2506.13131},
  eprint = {2506.13131},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2506.13131}
}

References

120 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. J. Abramson, J. Adler, J. Dunger, R. Evans, T. Green, A. Pritzel, O. Ronneberger, L. Willmore, A. J. Ballard, J. Bambrick, et al. Accurate structure prediction of biomolecular interactions with alphafold 3. Nature, 630(8016):493–500, 2024. find
  2. V. Aglietti, I. Ktena, J. Schrouff, E. Sgouritsa, F. J. R. Ruiz, A. Malek, A. Bellot, and S. Chiappa. FunBO: Discovering acquisition functions for Bayesian optimization with FunSearch. In International Conference on Machine Learning, 2025. find
  3. AlphaProof and AlphaGeometry teams. AI achieves silver-medal standard solving International Mathematical Olympiad problems, 2024. URL https://deepmind.g oogle/discover/blog/ai-solves-imo-problems-at-silver-medal-lev el . ↗
  4. D. Bahdanau, K. Cho, and Y. Bengio. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014. find our card
  5. W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming: An Introduction on the Automatic Evolution of computer programs and its Applications. The Morgan Kaufmann Series in Artificial Intelligence, 1998. find
  6. J. Bausch, A. W. Senior, F. J. H. Heras, T. Edlich, A. Davies, M. Newman, C. Jones, K. Satzinger, M. Y. Niu, S. Blackwell, G. Holland, D. Kafri, J. Atalaya, C. Gidney, D. Hassabis, S. Boixo, H. Neven, and P. Kohli. Learning high-accuracy error decoding for quantum processors. Nature, 635(8040):834–8… — [doi:10.1038/s41586-0](https://doi.org/10.1038/s41586-0) find
  7. D. A. Boiko, R. MacKnight, B. Kline, and G. Gomes. Autonomous chemical research with large language models. Nature, 624(7992):570–578, 2023. doi: 10.1038/s415 86-023-06792-0. find our card
  8. P. Boyvalenkov, S. Dodunekov, and O. Musin. A survey on the kissing numbers. Serdica Math. J., 38(4):507–522, 2012. ISSN 1310-6600. find
  9. J. Bradbury, R. Frostig, P. Hawkins, M. J. Johnson, C. Leary, D. Maclaurin, G. Necula, A. Paszke, J. VanderPlas, S. Wanderman-Milne, and Q. Zhang. JAX: composable transformations of Python+NumPy programs, 2018. URL http://github.com/j ax-ml/jax . ↗
  10. A. M. Bran, S. Cox, O. Schilter, C. Baldassari, A. D. White, and P. Schwaller. Augmenting large language models with chemistry tools. Nature Machine Intelligence, 6(5):525– 535, 2024. doi: 10.1038/s42256-024-00832-8. — [doi:10.1038/s42256-024-00832-8](https://doi.org/10.1038/s42256-024-00832-8) find
  11. A. M. Bran, T. A. Neukomm, D. P. Armstrong, Z. Jončev, and P. Schwaller. Chemical reasoning in LLMs unlocks steerable synthesis planning and reaction mechanism elucidation. In arXiv preprint arXiv:2503.08537, 2025. find
  12. M. Caldas Ramos, C. J. Collison, and A. D. White. A review of large language models and autonomous agents in chemistry. Chemical Science, 16:2514–2572, 2025. doi: 10.1039/D4SC03921A. find
  13. P. S. Castro, N. Tomasev, A. Anand, N. Sharma, R. Mohanta, A. Dev, K. Perlin, S. Jain, K. Levin, N. Éltető, W. Dabney, A. Novikov, G. C. Turner, M. K. Eckstein, N. D. Daw, K. J. Miller, and K. L. Stachenfeld. Discovering symbolic cognitive models from human and animal behavior. In International Conf… find
  14. A. Chen, D. M. Dohan, and D. R. So. EvoPrompting: Language models for code-level neural architecture search. In Advances in Neural Information Processing Systems, 2023. find
  15. T. Chen, B. Xu, and K. Devleker. Automating GPU kernel generation with DeepSeek-R1 and inference time scaling, 2025. URL https://developer.nvidia.com/blog/automating-gpu-kernel-generation-with-deepseek-r1-and-inference -time-scaling . ↗
  16. X. Chen, C. Liang, D. Huang, E. Real, K. Wang, H. Pham, X. Dong, T. Luong, C.-J. Hsieh, Y. Lu, and Q. V. Le. Symbolic discovery of optimization algorithms. Advances in Neural Information Processing Systems, 2023. find
  17. A. Cloninger and S. Steinerberger. On suprema of autoconvolutions with an application to Sidon sets. Proceedings of the American Mathematical Society, 145(8):3191–3200, 2017. find
  18. H. Cohn and F. Gonçalves. An optimal uncertainty principle in twelve dimensions via modular forms. Inventiones mathematicae, 217:799–831, 2019. find
  19. K. M. Collins, A. Q. Jiang, S. Frieder, L. Wong, M. Zilka, U. Bhatt, T. Lukasiewicz, Y. Wu, J. B. Tenenbaum, W. Hart, et al. Evaluating language models for mathematics through interactions. Proceedings of the National Academy of Sciences, 121(24):e2318124121, 2024. find
  20. K. D. Cooper, D. Subramanian, and L. Torczon. Adaptive optimizing compilers for the 21st century. The Journal of Supercomputing, 23:7–22, 2002. find
  21. M. Cranmer. Interpretable machine learning for science with pysr and symbolicregression. jl. arXiv preprint arXiv:2305.01582, 2023. find
  22. T. Dao, D. Fu, S. Ermon, A. Rudra, and C. Ré. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems, 35:16344–16359, 2022. find
  23. A. Davies, P. Veličković, L. Buesing, S. Blackwell, D. Zheng, N. Tomašev, R. Tanburn, P. Battaglia, C. Blundell, A. Juhász, M. Lackenby, G. Williamson, D. Hassabis, and P. Kohli. Advancing mathematics by guiding human intuition with AI. Nature, 600 (7887):70–74, 2021. doi: 10.1038/s41586-021-04086-x… — [doi:10.1038/s41586-021-04086-x](https://doi.org/10.1038/s41586-021-04086-x) find
  24. J. S. Ellenberg, C. S. Fraser-Taliente, T. R. Harvey, K. Srivastava, and A. V. Sutherland. Generative modelling for mathematical discovery. arXiv preprint arXiv:2503.11061, 2025. — [arXiv:2503.11061](https://arxiv.org/abs/2503.11061) find
  25. P. Erdős. Some remarks on number theory. Riveon Lematematika, 9:45–48, 1955. find
  26. A. Fawzi, M. Balog, A. Huang, T. Hubert, B. Romera-Paredes, M. Barekatain, A. Novikov, F. J. R. Ruiz, J. Schrittwieser, G. Swirszcz, D. Silver, D. Hassabis, and P. Kohli. Discovering faster matrix multiplication algorithms with reinforcement learning. Nature, 610(7930):47–53, 2022. doi: 10.1038/s415… find
  27. C. Fernando, D. Banarse, H. Michalewski, S. Osindero, and T. Rocktäschel. Promptbreeder: Self-referential self-improvement via prompt evolution. arXiv preprint arXiv:2309.16797, 2023. find our card
  28. N. Ferruz and B. Höcker. Controllable protein design with language models. Nature Machine Intelligence, 4(6):521–532, 2022. find
  29. E. Friedman. Erich’s Packing Center. https://erich-friedman.github.io/pa cking/ , 2025. Accessed: 2025-04-22. ↗
  30. F. Frohnert, X. Gu, M. Krenn, and E. van Nieuwenburg. Discovering emergent connections in quantum physics research via dynamic word embeddings. Machine Learning: Science and Technology, 6(1):015029, 2025. doi: 10.1088/2632-2153/adb00a. — [doi:10.1088/2632-2153/adb00a](https://doi.org/10.1088/2632-2153/adb00a) find
  31. M. Ganzhinov. Highly symmetric lines. In arXiv preprint arXiv:2207.08266v1, 2022. — [arXiv:2207.08266](https://arxiv.org/abs/2207.08266) find
  32. Gemini team. Gemini 2.5: Our most intelligent AI model, 2025. URL https: //blog.google/technology/google-deepmind/gemini-model-thinking-u pdates-march-2025 . find
  33. F. Gonçalves, D. O. e Silva, and S. Steinerberger. Hermite polynomials, linear flows on the torus, and an uncertainty principle for roots. Journal of Mathematical Analysis and Applications, 451(2):678–711, 2017. find
  34. J. Gottweis, W.-H. Weng, A. Daryin, T. Tu, A. Palepu, P. Sirkovic, A. Myaskovsky, F. Weissenberger, K. Rong, R. Tanno, K. Saab, D. Popovici, J. Blum, F. Zhang, K. Chou, A. Hassidim, B. Gokturk, A. Vahdat, P. Kohli, Y. Matias, A. Carroll, K. Kulkarni, N. Tomasev, Y. Guan, V. Dhillon, E. D. Vaishnav,… find our card
  35. A. Grayeli, A. Sehgal, O. Costilla Reyes, M. Cranmer, and S. Chaudhuri. Symbolic regression with a learned concept library. Advances in Neural Information Processing Systems, 37:44678–44709, 2024. find
  36. M. Gridach, J. Nanavati, C. Mack, K. Z. E. Abidine, and L. Mendes. Agentic AI for scientific discovery: A survey of progress, challenges, and future directions. In ICLR Workshop: Towards Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation, 2025. find
  37. X. Gu and M. Krenn. Interesting scientific idea generation using knowledge graphs and LLMs: Evaluations with 100 research group leaders. In arXiv preprint arXiv:2405.17044, 2024. — [arXiv:2405.17044](https://arxiv.org/abs/2405.17044) find
  38. S. Guo, A. H. Shariatmadari, G. Xiong, and A. Zhang. Embracing foundation models for advancing scientific discovery. In Proceedings of the IEEE International Conference on Big Data, pages 1746–1755, 2024. doi: 10.1109/bigdata62323.2024.10825618. — [doi:10.1109/bigdata62323.2024.10825618](https://doi.org/10.1109/bigdata62323.2024.10825618) find
  39. K. Gyarmati, F. Hennecart, and I. Z. Ruzsa. Sums and differences of finite sets. Functiones et Approximatio Commentarii Mathematici, 37(1):175–186, 2007. find
  40. J. K. Haugland. The minimum overlap problem revisited. arXiv:1609.08000, 2016. — [arXiv:1609.08000](https://arxiv.org/abs/1609.08000) find
  41. E. Hemberg, S. Moskal, and U.-M. O’Reilly. Evolving code with a large language model. Genetic Programming and Evolvable Machines, 25(2):21, 2024. doi: 10.1007/s10710-024-09494-2. — [doi:10.1007/s10710-024-09494-2](https://doi.org/10.1007/s10710-024-09494-2) find
  42. J. E. Hopcroft and L. R. Kerr. On minimizing the number of multiplications necessary for matrix multiplication. SIAM J. Appl. Math., 20(1):30–36, Jan. 1971. ISSN 0036-1399. doi: 10.1137/0120004. — [doi:10.1137/0120004](https://doi.org/10.1137/0120004) find
  43. K. Huang, Y. Qu, H. Cousins, W. A. Johnson, D. Yin, M. Shah, D. Zhou, R. Altman, M. Wang, and L. Cong. CRISPR-GPT: An LLM agent for automated design of gene-editing experiments. In arXiv preprint arXiv:2404.18021, 2024. find
  44. L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng, B. Qin, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 43(2): 1–55, 2025. find our card
  45. S. Jia, C. Zhang, and V. Fung. LLMatDesign: Autonomous materials discovery with large language models. In arXiv preprint arXiv:2406.13163, 2024. — [arXiv:2406.13163](https://arxiv.org/abs/2406.13163) find
  46. J. Jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvunakool, R. Bates, A. Žídek, A. Potapenko, A. Bridgland, C. Meyer, S. A. A. Kohl, A. J. Ballard, A. Cowie, B. Romera-Paredes, S. Nikolov, R. Jain, J. Adler, T. Back, S. Petersen, D. Reiman, E. Clancy, M. Zielinski, M.… find our card
  47. M. Kauers and J. Moosbauer. Flip graphs for matrix multiplication. In Proceedings of the 2023 International Symposium on Symbolic and Algebraic Computation, pages 381–388, 2023. arXiv preprint find
  48. M. Kauers and J. Moosbauer. Some new non-commutative matrix multiplication algorithms of size ( 𝑛, 𝑚, 6). ACM Commun. Comput. Algebra, 58(1):1–11, Jan. 2025. ISSN 1932-2232. doi: 10.1145/3712020.3712021. — [doi:10.1145/3712020.3712021](https://doi.org/10.1145/3712020.3712021) find
  49. M. Kauers and I. Wood. Consequences of the Moosbauer-Poole algorithms. arXiv preprint arXiv:2505.05896, 2025. — [arXiv:2505.05896](https://arxiv.org/abs/2505.05896) find
  50. D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR), 2015. find
  51. J. R. Koza. Genetic programming as a means for programming computers by natural selection. Statistics and Computing, 4(2):87–112, 1994. doi: 10.1007/BF00175355. — [doi:10.1007/bf00175355](https://doi.org/10.1007/bf00175355) find
  52. J. D. Laderman. A noncommutative algorithm for multiplying 3 × 3 matrices using 23 multiplications. Bulletin of the American Mathematical Society, 82(1):126 – 128, 1976. find
  53. R. Lam, A. Sanchez-Gonzalez, M. Willson, P. Wirnsberger, M. Fortunato, F. Alet, S. Ravuri, T. Ewalds, Z. Eaton-Rosen, W. Hu, A. Merose, S. Hoyer, G. Holland, O. Vinyals, J. Stott, A. Pritzel, S. Mohamed, and P. Battaglia. Learning skillful medium-range global weather forecasting. Science, 382(6677):… — [doi:10.1126/science.adi2336](https://doi.org/10.1126/science.adi2336) find
  54. W. B. Langdon and R. Poli. Foundations of genetic programming. Springer Science & Business Media, 2013. find
  55. R. Lange, Y. Tian, and Y. Tang. Large language models as evolution strategies. In Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO ’24 Companion, pages 579–582. Association for Computing Machinery, 2024. doi: 10.1145/3638530.3654238. find
  56. R. T. Lange, A. Prasad, Q. Sun, M. Faldor, Y. Tang, and D. Ha. The AI CUDA engineer: Agentic CUDA kernel discovery, optimization and composition. Technical report, Sakana AI, 02 2025. find
  57. J. Lehman, J. Gordon, S. Jain, K. Ndousse, C. Yeh, and K. O. Stanley. Evolution through large models. In Handbook of evolutionary machine learning, pages 331–366. Springer, 2023. find
  58. J. Lehman, J. Gordon, S. Jain, K. Ndousse, C. Yeh, and K. O. Stanley. Evolution Through Large Models, pages 331–366. Springer Nature Singapore, 2024. doi: 10.1007/978-981-99-3814-8\\\_11. — [doi:10.1007/978-981-99-3814-8\\\_11](https://doi.org/10.1007/978-981-99-3814-8\_11) find
  59. P.-H. Li, Y.-Y. Sun, H.-F. Juan, C.-Y. Chen, H.-K. Tsai, and J.-H. Huang. A large language model framework for literature-based disease–gene association prediction. Briefings in Bioinformatics, 26(1):bbaf070, 02 2025. ISSN 1477-4054. doi: 10.1093/bib/bbaf070. — [doi:10.1093/bib/bbaf070](https://doi.org/10.1093/bib/bbaf070) find
  60. Y. Li, D. Choi, J. Chung, N. Kushman, J. Schrittwieser, R. Leblond, T. Eccles, J. Keeling, F. Gimeno, A. D. Lago, T. Hubert, P. Choy, C. de Masson d’Autume, I. Babuschkin, X. Chen, P.-S. Huang, J. Welbl, S. Gowal, A. Cherepanov, J. Molloy, D. J. Mankowitz, E. S. Robson, P. Kohli, N. de Freitas, K. K… find our card
  61. H. Lin, M. Maas, M. Roquemore, A. Hasanzadeh, F. Lewis, Y. Simonson, T.-W. Yang, A. Yazdanbakhsh, D. Altinbüken, F. Papa, et al. ECO: An LLM-driven efficient code optimizer for warehouse scale computers. arXiv preprint arXiv:2503.15669, 2025. — [arXiv:2503.15669](https://arxiv.org/abs/2503.15669) find
  62. Z. Lin, H. Akin, R. Rao, B. Hie, Z. Zhu, W. Lu, N. Smetanin, R. Verkuil, O. Kabeli, Y. Shmueli, A. dos Santos Costa, M. Fazel-Zarandi, T. Sercu, S. Candido, and A. Rives. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science, 379(6637):1123–1130, 2023. doi: 1… — [doi:10.1126/science.ade2574](https://doi.org/10.1126/science.ade2574) find
  63. F. Liu, X. Tong, M. Yuan, X. Lin, F. Luo, Z. Wang, Z. Lu, and Q. Zhang. Evolution of heuristics: Towards efficient automatic algorithm design using large language model. arXiv preprint arXiv:2401.02051, 2024. — [arXiv:2401.02051](https://arxiv.org/abs/2401.02051) find
  64. F. Luo, J. Zhang, Q. Wang, and C. Yang. Leveraging prompt engineering in large language models for accelerating chemical research. ACS Central Science, 2025. doi: 10.1021/acscentsci.4c01935. — [doi:10.1021/acscentsci.4c01935](https://doi.org/10.1021/acscentsci.4c01935) find
  65. Z. Luo, Z. Yang, Z. Xu, W. Yang, and X. Du. LLM4SR: A survey on large language models for scientific research. In arXiv preprint arXiv:2501.04306, 2025. find
  66. H. Ma, A. Narayanaswamy, P. Riley, and L. Li. Evolving symbolic density functionals. Science Advances, 8(36):eabq0279, 2022. doi: 10.1126/sciadv.abq0279. — [doi:10.1126/sciadv.abq0279](https://doi.org/10.1126/sciadv.abq0279) find
  67. A. Madani, B. Krause, E. R. Greene, S. Subramanian, B. P. Mohr, J. M. Holton, J. L. Olmos, C. Xiong, Z. Z. Sun, R. Socher, J. S. Fraser, and N. Naik. Large language models generate functional protein sequences across diverse families. Nature Biotechnology, 41 (8):1099–1106, August 2023. ISSN 1087-01… — [doi:10.1038/s41587-022-01618-2](https://doi.org/10.1038/s41587-022-01618-2) find
  68. D. J. Mankowitz, A. Michi, A. Zhernov, M. Gelmi, M. Selvi, C. Paduraru, E. Leurent, S. Iqbal, J.-B. Lespiau, A. Ahern, T. Köppe, K. Millikin, S. Gaffney, S. Elster, J. Broshear, C. Gamble, K. Milan, R. Tung, M. Hwang, T. Cemgil, M. Barekatain, Y. Li, A. Mandhane, T. Hubert, J. Schrittwieser, D. Hass… find
  69. H. Massalin. Superoptimizer - A look at the smallest program. In R. H. Katz and M. Freeman, editors, Proceedings of the Second International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS II), Palo Alto, California, USA, October 5-8, 1987, pages 122–126.… — [doi:10.1145/36206.36194](https://doi.org/10.1145/36206.36194) find
  70. M. Matolcsi and C. Vinuesa. Improved bounds on the supremum of autoconvolutions. Journal of mathematical analysis and applications, 372(2):439–447, 2010. find
  71. S. Miret and N. M. A. Krishnan. Are LLMs ready for real-world materials discovery? In arXiv preprint arXiv:2402.05200, 2024. find
  72. J. Moosbauer and M. Poole. Flip graphs with symmetry and new matrix multiplication schemes. arXiv preprint arXiv:2502.04514, 2025. — [arXiv:2502.04514](https://arxiv.org/abs/2502.04514) find
  73. C. Morris, M. Jurado, and J. Zutty. Llm guided evolution-the automation of models advancing models. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 377–384, 2024. find
  74. J.-B. Mouret and J. Clune. Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909, 2015. — [arXiv:1504.04909](https://arxiv.org/abs/1504.04909) find
  75. V. Naumov, D. Zagirova, S. Lin, Y. Xie, W. Gou, A. Urban, N. Tikhonova, K. Alawi, M. Durymanov, F. Galkin, S. Chen, D. Sidorenko, M. Korzinkin, M. Scheibye-Knudsen, A. Aspuru-Guzik, E. Izumchenko, D. Gennert, F. W. Pun, M. Zhang, P. Kamya, A. Aliper, F. Ren, and A. Zhavoronkov. DORA AI scientist: Mu… — [doi:10.1101/2025.03.06.641840](https://doi.org/10.1101/2025.03.06.641840) find
  76. OpenAI. Introducing OpenAI o3 and o4-mini, 2025. URL https://openai.com/i ndex/introducing-o3-and-o4-mini/ . ↗
  77. OpenXLA. XLA: composable transformations of Python+NumPy programs. URL https://github.com/openxla/xla . ↗
  78. H. Pan, N. Mudur, W. Taranto, M. Tikhanovskaya, S. Venugopalan, Y. Bahri, M. P. Brenner, and E.-A. Kim. Quantum many-body physics calculations with large language models. Communications Physics, 8(1):49, 2025. doi: 10.1038/s42005-025-01956-y. — [doi:10.1038/s42005-025-01956-y](https://doi.org/10.1038/s42005-025-01956-y) find
  79. D. Pantiukhin, B. Shapkin, I. Kuznetsov, A. A. Jost, and N. Koldunov. Accelerating Earth science discovery via multi-agent LLM systems. In arXiv preprint arXiv:2503.05854, 2025. — [arXiv:2503.05854](https://arxiv.org/abs/2503.05854) find
  80. Z. Rasheed, M. Waseem, A. Ahmad, K.-K. Kemell, W. Xiaofeng, A. N. Duc, and P. Abrahamsson. Can large language models serve as data analysts? a multi-agent assisted approach for qualitative data analysis. arXiv preprint arXiv:2402.01386, 2024. — [arXiv:2402.01386](https://arxiv.org/abs/2402.01386) find
  81. S. Ren, P. Jian, Z. Ren, C. Leng, C. Xie, and J. Zhang. Towards scientific intelligence: A survey of LLM-based scientific agents. In arXiv preprint arXiv:2503.24047, 2025. find
  82. A. Rives, J. Meier, T. Sercu, S. Goyal, Z. Lin, J. Liu, D. Guo, M. Ott, C. L. Zitnick, J. Ma, and R. Fergus. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences, 118(15):e2016239118, 2021. doi:… — [doi:10.1073/pnas.2016239118](https://doi.org/10.1073/pnas.2016239118) find
  83. B. Romera-Paredes, M. Barekatain, A. Novikov, M. Balog, M. P. Kumar, E. Dupont, F. J. R. Ruiz, J. Ellenberg, P. Wang, O. Fawzi, P. Kohli, and A. Fawzi. Mathematical discoveries from program search with large language models. Nature, 625(7995): 468–475, 2023. doi: 10.1038/s41586-023-06924-6. find our card
  84. F. J. R. Ruiz, T. Laakkonen, J. Bausch, M. Balog, M. Barekatain, F. J. H. Heras, A. Novikov, N. Fitzpatrick, B. Romera-Paredes, J. van de Wetering, A. Fawzi, K. Meichanetzidis, and P. Kohli. Quantum circuit optimization with AlphaTensor. Nature Machine Intelligence, 7(3):374–385, 2025. doi: 10.1038/… — [doi:10.1038/s42256-025-01001-1](https://doi.org/10.1038/s42256-025-01001-1) find
  85. O. A. Sarumi and D. Heider. Large language models and their applications in bioinformatics. Computational and Structural Biotechnology Journal, 23:3498–3505, 2024. ISSN 2001-0370. doi: https://doi.org/10.1016/j.csbj.2024.09.031. — [doi:10.1016/j.csbj.2024.09.031](https://doi.org/10.1016/j.csbj.2024.09.031) ↗
  86. E. Schkufza, R. Sharma, and A. Aiken. Stochastic superoptimization. In V. Sarkar and R. Bodík, editors, Architectural Support for Programming Languages and Operating Systems, ASPLOS 2013, Houston, TX, USA, March 16-20, 2013, pages 305–316. ACM, 2013. doi: 10.1145/2451116.2451150. find
  87. M. Schmidt and H. Lipson. Distilling free-form natural laws from experimental data. Science, 324(5923):81–85, 2009. doi: 10.1126/science.1165893. — [doi:10.1126/science.1165893](https://doi.org/10.1126/science.1165893) find
  88. N. Shinn, F. Cassano, A. Gopinath, K. Narasimhan, and S. Yao. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36:8634–8652, 2023. find our card
  89. P. Shojaee, K. Meidani, S. Gupta, A. B. Farimani, and C. K. Reddy. LLM-SR: Scientific equation discovery via programming with large language models. In International Conference on Learning Representations, 2025. find
  90. C. Si, D. Yang, and T. Hashimoto. Can LLMs generate novel research ideas? a large-scale human study with 100+ NLP researchers. In International Conference on Learning Representations, 2025. find our card
  91. A. Smirnov. Several bilinear algorithms for matrix multiplication problems ⟨3 , 𝑃, 𝑄 ⟩. https://www.researchgate.net/publication/350897049\_Several\_Bilin ear\_Algorithms\_for\_Matrix\_Multiplication\_Problems\_3\_P\_Q , 04 2021. ↗
  92. A. Smirnov. Bilinear algorithm for matrix multiplication ⟨4 × 4 × 9; 104⟩. an irreducibly irrational solution of the brent system? https://www.researchgate.net/pub lication/364167198\_Bilinear\_Algorithm\_for\_Matrix\_Multiplication\_ 4x4x9\_104\_An\_irreducibly\_irrational\_solution\_of\_the\_Brent\_system , 10 2… ↗
  93. A. V. Smirnov. The bilinear complexity and practical algorithms for matrix multiplication. Computational Mathematics and Mathematical Physics, 53(12):1781–1795, 2013. find
  94. Z. Song, M. Ju, C. Ren, Q. Li, C. Li, Q. Zhou, and J. Wang. LLM-Feynman: Leveraging large language models for universal scientific formula and theory discovery. In arXiv preprint arXiv:2503.06512, 2025. — [arXiv:2503.06512](https://arxiv.org/abs/2503.06512) find
  95. V. Strassen. Gaussian elimination is not optimal. Numerische mathematik, 13(4): 354–356, 1969. find
  96. A. Surina, A. Mansouri, L. Quaedvlieg, A. Seddas, M. Viazovska, E. Abbe, and C. Gulcehre. Algorithm discovery with LLMs: Evolutionary search meets reinforcement learning. In arXiv preprint arXiv:2504.05108, 2025. find
  97. R. Tanese. Distributed genetic algorithms for function optimization. University of Michigan, 1989. find
  98. A. Thakur, G. Tsoukalas, Y. Wen, J. Xin, and S. Chaudhuri. An in-context learning agent for formal theorem-proving. In Conference on Language Models, 2024. find
  99. T. H. Trinh, Y. Wu, Q. V. Le, H. He, and T. Luong. Solving olympiad geometry without human demonstrations. Nature, 625(7995):476–482, 2024. find our card
  100. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In Advances in Neural Information Processing Systems, 2017. find
  101. P. Veličković, A. Vitvitskyi, L. Markeeva, B. Ibarz, L. Buesing, M. Balog, and A. Novikov. Amplifying human performance in combinatorial competitive programming. 2024. find
  102. A. Verma, L. Pedrosa, M. Korupolu, D. Oppenheimer, E. Tune, and J. Wilkes. Large-scale cluster management at Google with Borg. In Proceedings of the Tenth European Conference on Computer Systems, EuroSys ’15, New York, NY, USA, 2015. Association for Computing Machinery. ISBN 9781450332385. doi: 10.1… — [doi:10.1145/2741948.2741964](https://doi.org/10.1145/2741948.2741964) find
  103. S. Verma, A. Goyal, A. Mathur, A. Anand, and S. Ranu. GRAIL: Graph edit distance and node alignment using llm-generated code. In International Conference on Machine Learning, 2025. find
  104. C. Vinuesa del Rio. Generalized Sidon sets. PhD thesis, Universidad Autónoma de Madrid, 2010. find
  105. H. Wang, M. Skreta, C. T. Ser, W. Gao, L. Kong, F. Strieth-Kalthoff, C. Duan, Y. Zhuang, Y. Yu, Y. Zhu, Y. Du, A. Aspuru-Guzik, K. Neklyudov, and C. Zhang. Efficient evolutionary search over chemical space with large language models. In International Conference on Learning Representations, 2025. find
  106. Q. Wang, D. Downey, H. Ji, and T. Hope. SciMON: Scientific inspiration machines optimized for novelty. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 279–299, Bangkok, Thailand, 2024. Association for Computational Linguistics… find
  107. E. P. White. A new bound for Erdős’ minimum overlap problem. Acta Arithmetica, 208:235–255, 2023. find
  108. Q. Wu, G. Bansal, J. Zhang, Y. Wu, B. Li, E. Zhu, L. Jiang, X. Zhang, S. Zhang, J. Liu, A. H. Awadallah, R. W. White, D. Burger, and C. Wang. AutoGen: Enabling next-gen LLM applications via multi-agent conversation. In arXiv preprint arXiv:2308.08155, 2023. find our card
  109. Y. Xia, P. Jin, S. Xie, L. He, C. Cao, R. Luo, G. Liu, Y. Wang, Z. Liu, Y.-J. Chen, Z. Guo, Y. Bai, P. Deng, Y. Min, Z. Lu, H. Hao, H. Yang, J. Li, C. Liu, J. Zhang, J. Zhu, R. Bi, K. Wu, W. Zhang, K. Gao, Q. Pei, Q. Wang, X. Liu, Y. Li, H. Zhu, Y. Lu, M. Ma, Z. Wang, T. Xie, K. Maziarz, M. Segler,… — [arXiv:2502.07527](https://arxiv.org/abs/2502.07527) find
  110. K. Yang, A. Swope, A. Gu, R. Chalamala, P. Song, S. Yu, S. Godil, R. J. Prenger, and A. Anandkumar. Leandojo: Theorem proving with retrieval-augmented language models. Advances in Neural Information Processing Systems, 36:21573–21612, 2023. find our card
  111. K. Yang, G. Poesia, J. He, W. Li, K. Lauter, S. Chaudhuri, and D. Song. Formal mathematical reasoning: A new frontier in AI. arXiv preprint arXiv:2412.16075, 2024. find
  112. Z. Yang, X. Du, J. Li, J. Zheng, S. Poria, and E. Cambria. Large language models for automated open-domain scientific hypotheses discovery. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13545–13565. Association for Computational Linguistics, 2024. doi: 10.18653/v1/202… find
  113. Z. Yang, W. Liu, B. Gao, T. Xie, Y. Li, W. Ouyang, S. Poria, E. Cambria, and D. Zhou. MOOSE-Chem: Large language models for rediscovering unseen chemistry scientific hypotheses. In International Conference on Learning Representations, 2025. find
  114. S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR), 2023. find our card
  115. S. Yao, F. Liu, X. Lin, Z. Lu, Z. Wang, and Q. Zhang. Multi-objective evolution of heuristic using large language model. In AAAI Conference on Artificial Intelligence, volume 39, pages 27144–27152, 2025. doi: 10.1609/aaai.v39i25.34922. — [doi:10.1609/aaai.v39i25.34922](https://doi.org/10.1609/aaai.v39i25.34922) find
  116. G. Ye, X. Cai, H. Lai, X. Wang, J. Huang, L. Wang, W. Liu, and X. Zeng. DrugAssist: A large language model for molecule optimization. In arXiv preprint arXiv:2401.10334, 2023. — [arXiv:2401.10334](https://arxiv.org/abs/2401.10334) find
  117. H. Ye, J. Wang, Z. Cao, F. Berto, C. Hua, H. Kim, J. Park, and G. Song. ReEvo: Large language models as hyper-heuristics with reflective evolution. In Advances in Neural Information Processing Systems, volume 37, 2024. find
  118. F. Zhang, S. Nguyen, Y. Mei, and M. Zhang. Genetic Programming for Production Scheduling. Springer, 2021. find
  119. H. Zhang, Y. Song, Z. Hou, S. Miret, and B. Liu. HoneyComb: A flexible LLM-based agent system for materials science. In Y. Al-Onaizan, M. Bansal, and Y.-N. Chen, editors, Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3369–3382. Association for Computational Linguistics… find
  120. Y. Zhou, H. Liu, T. Srivastava, H. Mei, and C. Tan. Hypothesis generation with large language models. In L. Peled-Cohen, N. Calderon, S. Lissak, and R. Reichart, editors, Proceedings of the 1st Workshop on NLP for Science (NLP4Science), pages 117–139. Association for Computational Linguistics, 2024.… find