Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judging each local edit only by its immediate score can discard useful intermediate states. We introduce AtomSearch, which keeps revision actions local while using subsequent skill states to guide search. Contrastive atomic editing links each primitive rule edit to failed and successful executions, a behavioral hypothesis, and an intended scope. Skill-State Tree Search (STS) evaluates short edit compositions and selectively retains them as executable states that can be revisited and extended. Outcome memory supplies later proposals with observed repair and regression statistics. We evaluate AtomSearch across four tasks and five target models. With deepseek-v4-flash, it exceeds SkillOpt on three of four tasks, including a 9.68-percentage-point gain on LiveMathematicianBench, and SkillOpt's final skills contain 2.3-19.7 times as many characters. In 67% of completed searches, the best validation state passes through an ancestor that was not highest-scoring at its depth. These results show how local rule edits can support the exploration of useful revision paths and yield compact skills, with additional offline evaluations used to explore alternative states.
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Tianjin University(天津大学);Southern Cross University(南方十字大学);School of Cybersecurity, Tianjin University(安全学院,天津大学);Nanyang Technological University(南洋理工大学);University of New South Wales(新南威尔士大学);Griffith University(格里菲斯大学)
From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
University of Science and Technology of China(中国科学技术大学);Hong Kong Polytechnic University(香港理工大学);Fuzhou University(福州大学);Xi’an Jiaotong University(西安交通大学)
OpenSkill: Open-World Self-Evolution for LLM Agents
Lehigh University(莱维大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校);University of British Columbia(不列颠哥伦比亚大学);Vector Institute(向量研究所);Salesforce AI Research(Salesforce人工智能研究);Massachusetts General Hospital and Harvard Medical School(麻省总医院和哈佛医学院)
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
Key Laboratory of Computational Linguistics, Ministry of Education, Peking University(计算语言学重点实验室,教育部,北京大学);School of Computer Science, Peking University(北京大学计算机学院);Department of Chinese Language and Literature, Peking University(北京大学中文语言文学系)
Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation
Korea University Sejong Campus(韩国大学世宗校区);Cardiff Metropolitan University(卡迪夫 Metropolitan 大学);Seoul National University(首尔国立大学);Bugil Academy(Bugil 学院);Gyeonggi Provincial Office of Education(京畿省教育厅);Loughborough University(洛桑大学);Korea National University of Education(韩国教育大学);Korea University(韩国大学);Korean Educational Development Institute(韩国教育发展院);Sungshin Women’s University(顺天堂女子大学);Seoul National University of Education(首尔国立教育大学);Korea Institute for Curriculum and Evaluation(韩国课程评价院);Indiana University Bloomington(印第安纳大学布卢明顿分校)
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
Intelligent Software Research Center, Institute of Software, CAS(中国科学院软件研究所智能软件研究中心);SKL of Processors, Institute of Computing Technology, CAS(中国科学院计算技术研究所处理器国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Cambricon Technologies(寒武纪科技);University of Science and Technology of China(中国科学技术大学)
Exposía: Teaching and Assessment of Academic Writing Skills for Research Project Proposals and Peer Feedback
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt(普遍知识处理实验室(UKP实验室)、计算机科学系和海斯曼人工智能中心(hessian.AI)、达姆施塔特技术大学);Department of Computer Science at Queens College, City University of New York (CUNY)(纽约城市大学皇后学院计算机科学系)
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
The University of Sydney(悉尼大学);University of Queensland(昆士兰大学);Southeast University(东南大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering
Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida(佛罗里达大学健康结局与生物医学信息学系,医学院);PAMI Research Group, Department of Computer and Information Science, Faculty of Science and Technology, University of Macau(澳门大学科学与技术学院计算机与信息科学系PAMI研究组)