University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）；Cornell University（康奈尔大学）；Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）；Simular
Saaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega, Bhuvan Chandra Koduru, Chih-Lun Li, Jiachen Yang, Ang Li, Xin Eric Wang
计算机使用智能体受限于人类为其提供的界面。智能体可能会逐个单元格地在电子表格中输入内容，而实际上只需一行代码即可完成；或者通过Shell打印出一个文件的全部2000行内容来查找某个函数。界面以及何时使用何种界面的知识均为手动构建，无法跟上新应用、工作流和模型的发展速度。本文提出，界面设计本身应成为智能体的一项能力。我们引入Agent S4，这是一款自主计算机使用智能体，可基于任务经验构建演化智能体界面。一个元智能体在合成训练任务上检查任务智能体的轨迹（无需成功标签），并在一个存储库中构建和修改界面与使用知识。随后，基于种群的演化通过元智能体从未见过的验证任务上的表现来选择哪些存储库需要进一步开发，偏好那些能泛化到已见任务之外的变更。在OSWorld V2上，搭载Qwen3.8-27B及演化后的界面存储库的Agent S4，在开源计算机使用智能体中创下新的最优性能，达到21.3%的二元得分，是使用固定界面的同模型性能的3.8倍。该性能超过GPT-5.5（13.0%）和Claude Opus 4.8（20.6%），而成本仅为后者的约4.3%和1.5%。在ScienceBoard上，使用相同模型时，演化后的界面将成功率从41.4%提升至58.6%。这些结果表明，可从经验中演化出有用的界面，使自主界面设计成为与模型及工具改进互补的提升来源。我们在该https URL开源了代码。
英文摘要：
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the knowledge of when to use each are built by hand, which cannot keep pace with new applications, workflows, and models. We argue that interface design should itself be an agent capability. We introduce Agent S4, an autonomous computer-use scientist that builds Evolving Agent Interfaces from task experience. A meta-agent examines task agents' trajectories on synthetic training tasks, without success labels, and constructs and revises interfaces and usage knowledge in a repository. Population-based evolution then selects which repositories to develop further by their performance on validation tasks the meta-agent never sees, favoring changes that generalize beyond the seen tasks. On OSWorld V2, Agent S4, with Qwen3.8-27B and the evolved repository of interfaces, sets a new state of the art in open-source computer-use agents, reaching 21.3% binary score, 3.8 times the same model with fixed interfaces. This is above both GPT-5.5 (13.0%) and Claude Opus 4.8 (20.6%), at about 4.3% and 1.5% of their respective costs. On ScienceBoard, the evolved interfaces improve the success rate from 41.4% to 58.6% with the same model. These results suggest that useful interfaces can be evolved from experience, making autonomous interface design a source of improvement complementary to advances in models and harnesses. We open-source our code at https://github.com/simular-ai/agent-s.
Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective
School of Computer Science and Engineering, The University of New South Wales（新南威尔士大学计算机科学与工程学院）；Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）；School of Data Science, The Chinese University of Hong Kong-Shenzhen（香港中文大学（深圳）数据科学学院）；Zhejiang Gongshang University（浙江工商大学）
From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）；College of Computer Science and Technology, Jilin University（计算机科学与技术学院，吉林大学）；Department of Electrical and Computer Engineering, Western University（电气与计算机工程系，西方大学）；Department of Electrical and Computer Engineering, Auburn University（电气与计算机工程系，阿伯茨罕大学）；School of Electrical and Computer Engineering, University of Sydney（电气与计算机工程学院，悉尼大学）
MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration
Queen Mary University of London（伦敦玛丽女王大学）；Duke Kunshan University（昆山杜克大学）；Hong Kong University of Science and Technology（香港科技大学）；School of Engineering, Westlake University（西湖大学工学院）；Research Center for Industries of the Future, Westlake University（西湖大学未来产业研究中心）
RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（未来区块链与隐私计算北京高精尖创新中心）；School of Artificial Intelligence（人工智能学院）；Beihang University（北京航空航天大学）；Tsinghua University（清华大学）；Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）
OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence
School of Software Technology, Zhejiang University（浙江大学软件学院）；Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, Zhejiang Gongshang University（浙江工商大学共同富裕统计监测与智能治理实验室）；Tongyi Lab, Alibaba Group（阿里集团通义实验室）；Alibaba Cloud（阿里云）
CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；McGill University（麦吉尔大学）；Columbia University（哥伦比亚大学）；Zhejiang University（浙江大学）；University of British Columbia（不列颠哥伦比亚大学）
Nanyang Technological University（南洋理工大学）；Stanford University（斯坦福大学）；Princeton University（普林斯顿大学）；City University of Hong Kong（香港城市大学）；University of Science and Technology of China（中国科学技术大学）
TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments
Eindhoven University of Technology（埃因霍温理工大学）；University of Oxford（牛津大学）；VulpiVox Intelligence（VulpiVox智能公司）；Squirrel Ai Learning（Squirrel AI学习公司）；Griffith University（格里菲斯大学）
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
Princeton University（普林斯顿大学）；Princeton AI Lab（普林斯顿人工智能实验室）；Tsinghua University（清华大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Sydney（悉尼大学）；Shanghai Jiao Tong University（上海交通大学）；Pennsylvania State University（宾夕法尼亚州立大学）；University of Michigan（密歇根大学）；Oregon State University（俄勒冈州立大学）；The Chinese University of Hong Kong（香港中文大学）；Fudan University（复旦大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；The University of Hong Kong（香港大学）；University of California, Santa Barbara（加州大学圣芭芭拉分校）；University of California San Diego（加州大学圣地亚哥分校）；University of Edinburgh（爱丁堡大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
University of Pennsylvania（宾夕法尼亚大学）；Brown University（布朗大学）；Nanyang Technological University（南洋理工大学）；University of Notre Dame（圣母大学）；George Mason University（乔治梅森大学）
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
University of Chinese Academy of Sciences（中国科学院大学）；Microsoft（微软公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Nanjing University（南京大学）
CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学与工程学院）；Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）；Big Data Institute, Central South University（中南大学大数据研究院）
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
University of Glasgow（格拉斯哥大学）；University of Sheffield（谢菲尔德大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；National University of Singapore（新加坡国家大学）；University of Cambridge（剑桥大学）；University College London（伦敦大学学院）；University of Aberdeen（阿伯丁大学）；Leiden University（莱顿大学）
CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Central South University（中南大学）；College of Computer Science, Sichuan University（四川大学计算机学院）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）
