AlphaEvolve: Gemini-powered coding agent scaling impact across fields

AlphaEvolve：基于 Gemini 的编程智能体，助力多领域实现规模化突破

In genomics, AlphaEvolve was used to improve DeepConsensus—a model developed by Google Research for correcting DNA sequencing errors— achieving a 30% reduction in variant detection errors. These improvements are helping scientists at PacBio analyze genetic data more accurately and at a lower cost. 在基因组学领域，AlphaEvolve 被用于改进 DeepConsensus（由 Google Research 开发，旨在纠正 DNA 测序错误），成功将变异检测错误率降低了 30%。这些改进正帮助 PacBio 的科学家们以更低的成本、更精准地分析遗传数据。

“The solution the Google team discovered using AlphaEvolve unlocks meaningfully higher accuracy rates for our sequencing instruments. For researchers, this higher-quality data might enable the discovery of previously hidden disease causing mutations.” — Aaron Wenger, Senior Director at PacBio “Google 团队利用 AlphaEvolve 发现的解决方案，显著提升了我们测序仪的准确率。对于研究人员而言，这些更高质量的数据或许能帮助发现此前难以察觉的致病突变。”—— PacBio 高级总监 Aaron Wenger

In grid optimization, AlphaEvolve was applied to the AC Optimal Power Flow problem. It helped increase the ability of our trained Graph Neural Network (GNN) model to find feasible solutions for the problem from 14% to over 88%, significantly reducing the need for other costly post-processing steps for electricity grids. 在电网优化方面，AlphaEvolve 被应用于交流最优潮流（AC Optimal Power Flow）问题。它帮助我们将训练好的图神经网络（GNN）模型寻找可行解的能力从 14% 提升至 88% 以上，大幅减少了电网运行中对其他昂贵后处理步骤的需求。

In earth sciences, AlphaEvolve translated complex geospatial data into more reliable, actionable insights. By helping automate the optimization of Earth AI models, the overall accuracy of predicting the risk of natural disaster—aggregated across 20 categories such as wildfires, floods, and tornadoes—was increased by 5%. 在地球科学领域，AlphaEvolve 将复杂的地理空间数据转化为更可靠、可操作的洞察。通过助力地球 AI 模型的自动化优化，自然灾害风险预测的整体准确率（涵盖野火、洪水和龙卷风等 20 个类别）提升了 5%。

In quantum physics, AlphaEvolve’s optimizations have made it possible to run complex molecular simulations on Google’s Willow quantum processor by suggesting quantum circuits with 10x lower error than previous conventionally optimized baselines. This has enabled immediate impactful contributions to first-of-a-kind experimental demonstrations of quantum computing — and it points toward a future where AlphaEvolve helps find algorithms that exceed the capabilities of classical computers. 在量子物理领域，AlphaEvolve 的优化方案通过提供比传统优化基准低 10 倍误差的量子电路，使得在 Google 的 Willow 量子处理器上运行复杂的分子模拟成为可能。这为量子计算的首创性实验演示做出了直接且重大的贡献，并预示着未来 AlphaEvolve 将助力发现超越经典计算机能力的算法。

Working with world-renowned mathematicians like Terence Tao, the system has helped solve Erdős problems. 通过与陶哲轩（Terence Tao）等世界知名数学家合作，该系统已成功帮助解决了一些埃尔德什（Erdős）问题。

“Tools such as AlphaEvolve are giving mathematicians very useful new capabilities. For optimization problems in particular, we can now quickly test potential inequalities for counterexamples, or to confirm our beliefs in what the extremizers are, which greatly improves our intuition about these problems and allows us to find rigorous proofs more readily.” — Terence Tao, Professor of Mathematics at UCLA “像 AlphaEvolve 这样的工具为数学家提供了非常有用的新能力。特别是在优化问题上，我们现在可以快速测试潜在不等式的反例，或者验证我们对极值点（extremizers）的猜想。这极大地提升了我们对这些问题的直觉，并使我们能够更轻松地找到严谨的证明。”—— 加州大学洛杉矶分校（UCLA）数学教授陶哲轩

AlphaEvolve has also broken records for classic mathematical challenges, including improving lower bounds for the Traveling Salesman Problem and Ramsey Numbers. AlphaEvolve 还打破了多项经典数学挑战的纪录，包括改进了旅行商问题（Traveling Salesman Problem）和拉姆齐数（Ramsey Numbers）的下界。

AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms AlphaEvolve：用于设计高级算法的 Gemini 驱动编程智能体

May 2025 | Science | Learn more 2025 年 5 月 | 科学 | 了解更多