Agile hardware design flows are a critically needed force multiplier to meet the exploding demand for compute. Recently, agentic generative AI systems have demonstrated significant advances in algorithm design, improving code efficiency, and enabling discovery across scientific domains.
Bridging these worlds, we present ArchAgent, an automated computer architecture discovery system built on AlphaEvolve. We show ArchAgent's ability to automatically design/implement state-of-the-art (SoTA) cache replacement policies (architecting new mechanisms/logic, not only changing parameters), broadly within the confines of an established cache replacement policy design competition.
In two days without human intervention, ArchAgent generated a policy achieving a 5.3% IPC speedup improvement over the prior SoTA on public multi-core Google Workload Traces. On the heavily-explored single-core SPEC06 workloads, it generated a policy in just 18 days showing a 0.9% IPC speedup improvement over the existing SoTA (a similar "winning margin" as reported by the existing SoTA). ArchAgent achieved these gains 3-5x faster than prior human-developed SoTA policies.
Agentic flows also enable "post-silicon hyperspecialization" where agents tune runtime-configurable parameters exposed in hardware policies to further align the policies with a specific workload (mix). Exploiting this, we demonstrate a 2.4% IPC speedup improvement over prior SoTA on SPEC06 workloads.
Finally, we outline broader implications for computer architecture research in the era of agentic AI. For example, we demonstrate the phenomenon of "simulator escapes", where the agentic AI flow discovered and exploited a loophole in a popular microarchitectural simulator - a consequence of the fact that these research tools were designed for a (now past) world where they were exclusively operated by humans acting in good-faith.
Trade-offs in Decentralized Agentic AI Discovery Across the Compute Continuum
Department of Computer Science(计算机科学系);University of Pisa(比萨大学);Institute of Information Science and Technologies(信息科学与技术研究所);National Research Council of Italy(意大利国家研究理事会);Institute of Informatics and Telematics(信息学与电信研究所)
ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AI
Department of Economics, Statistics and Business, Universitas Mercatorum, Rome, Italy(经济学、统计学与商业系,墨菲大学,罗马,意大利);Department of Engineering and Science, Universitas Mercatorum, Rome, Italy(工程与科学系,墨菲大学,罗马,意大利);Independent Researcher, Bucharest, Romania(独立研究者,布加勒斯特,罗马尼亚)
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
École nationale des chartes – PSL(国立文献学校(巴黎文理研究大学));EPITA(EPITA 工程师学院);EPITA Research Laboratory(EPITA 研究实验室);Geneva Graduate Institute(日内瓦高等国际关系及发展学院)
Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Institute for Advanced Study in Mathematics, Harbin Institute of Technology(哈尔滨工业大学数学研究院);School of Mathematics, Harbin Institute of Technology(哈尔滨工业大学数学学院);School of Chemistry and Molecular Engineering, East China Normal University(华东师范大学化学与分子工程学院);Department of Chemistry, Fudan University(复旦大学化学系);Department of Electronic Engineering, Tsinghua University(清华大学电子工程系);School of Chemical Science and Engineering, Tongji University(同济大学化学科学与工程学院)
System of Agentic AI for the Discovery of Metal-Organic Frameworks
University of California, Berkeley(加州大学伯克利分校);Lawrence Berkeley National Laboratory(伯克利国家实验室);Google DeepMind(谷歌DeepMind);Kavli Energy NanoScience Institute(Kavli能源纳米科学研究所)
Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
Department of Statistics, Virginia Tech(统计学系,弗吉尼亚理工学院);Department of Statistical Science, Baylor University(统计科学系,贝勒大学);Advanced Research Computing, Virginia Tech(高级研究计算,弗吉尼亚理工学院)
See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs
Indian Institute of Technology Delhi(印度德里理工学院);Robert Bosch GmbH(罗伯特·博世有限公司);TCS Research(塔塔咨询服务公司研究院);Yardi School of Artificial Intelligence (ScAI)(亚迪人工智能学院);Department of Applied Mechanics(应用力学系)
FRAGMENTA: Efficient End-to-end Fragmentation-based Generative Model with Agentic Tuning for Drug Lead Optimization in Small Data Regime
Department of Computer Science and Engineering(计算机科学与工程系);University of Colorado Denver(科罗拉多大学丹佛分校);Skaggs School of Pharmacy(斯卡格斯药学院);University of Colorado Anschutz Medical Campus(科罗拉多大学安舒茨医疗分校)
EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉科学学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twins
University Côte d’Azur(蔚蓝海岸大学);Cancer Research Center of Marseille(马赛癌症研究中心);Institut Paoli-Calmettes(保利-卡尔梅特研究所);Mines Paris(巴黎矿业学院);PSL University(巴黎文理研究大学);Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);Institut Galien Paris-Saclay(巴黎萨克雷加利安研究所);University of Cambridge(剑桥大学)
Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
Laboratory for Atomistic and Molecular Mechanics(原子分子力学实验室);Department of Biological Engineering(生物工程系);Massachusetts Institute of Technology(麻省理工学院);Department of Civil and Environmental Engineering(土木与环境工程系);Department of Mechanical Engineering(机械工程系);Center for Computational Science and Engineering(计算科学与工程中心);Schwarzman College of Computing(施瓦茨曼计算学院)
Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3
University of Vermont(弗吉尼亚大学);Larner College of Medicine, University of Vermont(弗吉尼亚大学医学学院);Purdue University(普渡大学);Department of Comparative Pathobiology(比较病理科部门);Department of Horticulture and Landscape Architecture(园艺与景观建筑部门);Department of Industrial and Molecular Pharmaceutics(工业与分子药学部门)
Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing
College of Electronics and Information Engineering, Shenzhen University(深圳大学电子与信息工程学院);School of Informatics, Xiamen University(厦门大学信息学院);School of Computer Science and Cyber Engineering, Guangzhou University(广州大学计算机科学与网络工程学院)
Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
Kavli Institute for Theoretical Physics, University of California Santa Barbara(加州大学圣芭芭拉分校凯文利理论物理研究所);Center for Gravitational Physics, University of Texas at Austin(德克萨斯大学奥斯汀分校重力物理中心);Department of Physics, University of California at Santa Barbara(加州大学圣芭芭拉分校物理系);International Centre for Theoretical Sciences, Tata Institute of Fundamental Research(塔塔基础研究机构国际理论科学研究中心);School of Natural Sciences, Institute for Advanced Study(高级研究院自然科学学院);Chennai Mathematical Institute(钦奈数学研究所);Kavli Institute for Cosmological Physics, The University of Chicago(芝加哥大学凯文利宇宙物理研究所);Department of Particle Physics & Astrophysics, Weizmann Institute of Science(魏茨曼科学研究所粒子物理与天体物理系)
Autonomous computational catalysis through an agentic research system
Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials, State Key Laboratory of Chemical Engineering and Low- Carbon Technology, Department of Chemical Engineering, Tsinghua University(北京先进化工材料人工智能重点实验室、化学工程与低碳技术国家重点实验室、清华大学化学工程系)