AlphaEvolve

AlphaEvolve is an evolutionary coding agent for designing advanced algorithms based on large language models such as Gemini. It was developed by Google DeepMind and unveiled in May 2025.[1][2]

Design

AlphaEvolve aims to autonomously discover and refine algorithms through a combination of large language models (LLMs) and evolutionary computation.[3] AlphaEvolve needs an evaluation function with metrics to optimize, and an initial algorithm. At each step, AlphaEvolve uses the LLM to produce variants of the existing algorithms, and then selects the most effective ones.[4] Unlike domain-specific predecessors like AlphaFold or AlphaTensor, AlphaEvolve is designed as a general-purpose system. It can operate across a wide array of scientific and engineering tasks by automatically modifying code and optimizing for multiple objectives. Its architecture allows it to evaluate code programmatically, reducing reliance on human input and mitigating risks such as hallucinations common in standard LLM outputs.[2]

Achievements

According to Google, across a selection of 50 open mathematical problems, the model was able to rediscover state-of-the-art solutions 75% of the time and discovered improved solutions 20% of the time, for example advancing the kissing number problem.[3] AlphaEvolve was also used to optimize Google's computing ecosystem. Improved data center scheduling heuristics, enabled the recovery of 0.7% of stranded resources. It was also used to optimize TPU circuit design and Gemini's training matrix multiplication kernel.[3]

Open source implementations

Following the publication of AlphaEvolve, several open source implementations have been developed by the research community.

One such implementation is OpenEvolve,[5] which implements distributed evolutionary algorithms, multi-language support, integration with various large language model providers, and automated discovery of high-performance GPU kernels that outperform expert-engineered baselines.[6]

See also

References

  1. ^ "AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms". Google DeepMind. 2025-05-14. Retrieved 2025-05-14.
  2. ^ a b Whitwam, Ryan (2025-05-14). "Google DeepMind creates super-advanced AI that can invent new algorithms". Ars Technica. Retrieved 2025-05-17.
  3. ^ a b c Nuñez, Michael (2025-05-14). "Meet AlphaEvolve, the Google AI that writes its own code—and just saved millions in computing costs". VentureBeat. Archived from the original on 2025-05-16. Retrieved 2025-05-14.
  4. ^ Tardif, Antoine (2025-05-17). "AlphaEvolve: Google DeepMind's Groundbreaking Step Toward AGI". Unite.AI. Retrieved 2025-05-25.
  5. ^ Sharma, Asankhaya. "OpenEvolve: Open-source implementation of AlphaEvolve". GitHub. Retrieved 2025-08-05.
  6. ^ Sharma, Asankhaya (2025-05-17). "OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve". Hugging Face. Retrieved 2025-08-05.

Content Disclaimer

Informasi ini disarikan dari Wikipedia dan disajikan kembali untuk tujuan edukasi. Konten tersedia di bawah lisensi CC BY-SA 3.0. Kami tidak bertanggung jawab atas ketidakakuratan data yang bersumber dari kontribusi publik tersebut.

  1. The information displayed on this website is sourced in part or in whole from Wikipedia and has been adapted for the purpose of restating it. We strive to provide accurate and relevant information, however:
  2. There is no guarantee of absolute accuracy. Wikipedia is an open, collaborative project that can be edited by anyone, so information is subject to change.
  3. It is not intended to constitute professional advice. The content displayed is for informational and educational purposes only. For important decisions (e.g., medical, legal, or financial), please consult a professional.
  4. Content copyright. Wikipedia is licensed under the Creative Commons Attribution-ShareAlike License (CC BY-SA). This means that content may be reused with appropriate attribution and shared under a similar license.
  5. Responsible use. Any risk arising from the use of information from this website is entirely the responsibility of the user.