通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2601.03509cs.AIcs.NE
演化式程序化技能网络
Evolving Programmatic Skill Networks
DIRO & Institut Courtois, Université de Montréal（DIRO与Courtois研究所，蒙特利尔大学）；Mila – Québec AI Institute（魁北克人工智能研究所）；Microsoft Research（微软研究院）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)~\opreflect for structured fault localization over skill compositions, (2)~progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3)~canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.
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）
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Nanyang Technological University（南洋理工大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Tsinghua University（清华大学）
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
Shanghai Jiao Tong University（上海交通大学）；Eastern Institute of Technology（东部技术研究所）；University of Science and Technology of China（中国科学技术大学）；Southeast University（东南大学）；Ningbo Institute of Digital Twin（宁波数字孪生研究所）
SkillFocus: Evolving Agent Skills via Capability Decomposition
East China Normal University（华东师范大学）；Nanyang Technological University（南洋理工大学）；Southern University of Science and Technology（南方科技大学）；Shanghai Innovation Institute（上海创新研究院）
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
University of Maryland（马里兰大学）；University of Southern California（南加州大学）；Good Start Labs（Good Start实验室）；Independent Researcher（独立研究者）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Ant Group（蚂蚁集团）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Hangzhou Dianzi University（杭州电子科技大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Xi’an Jiaotong University（西安交通大学）
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
Shenzhen International Center for Industrial and Applied Mathematics（深圳国际工业与应用数学中心）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Shenzhen Loop Area Institute（深圳河套学院）
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Huazhong University of Science and Technology（华中科技大学）
Fudan University（复旦大学）；Shanghai Key Laboratory of Data Science（上海市数据科学重点实验室）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）
Stony Brook University（石溪大学）；Allen Institute for AI（艾伦人工智能研究所）
Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR representations to programmatically create hard-to-cheat synthetic contexts for real questions in six multi-step reasoning datasets. These contexts are carefully designed to avoid reasoning shortcuts prevalent in real contexts that prevent models from learning the right skills. This results in a pretraining dataset, named TeaBReaC, containing 525K multi-step questions…
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
State Key Laboratory of Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学）；School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学）；School of Intelligence Science and Technology, Nanjing University, China（智能科学与技术学院，南京大学）；Centre for Frontier AI Research（前沿人工智能研究中心）；Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，新加坡科技研究局）；Department of Computer Science and Engineering, Hong Kong University of Science and Technology, China（香港科学与技术大学计算机科学与工程系）
Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
Southwest Jiaotong University, China（西南交通大学）；The University of Tokyo, Japan（东京大学）；RIKEN, Japan（日本理化学研究所）；Westlake University, China（西湖大学）；Hokkaido University, Japan（北海道大学）
PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）；Shanghai AI Laboratory（上海人工智能实验室）；School of Psychology and Cognitive Science, East China Normal University（东华大学心理学与认知科学学院）
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Dalian University of Technology（大连理工大学）；Fudan University（复旦大学）；University of Oxford（牛津大学）；North China Electric Power University（华北电力大学）；The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tianjin University（天津大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；National University of Singapore（新加坡国立大学）
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
The Hong Kong University of Science and Technology（香港科学与技术大学）；Harbin Institute of Technology（哈尔滨工业大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Nanjing University（南京大学）；The University of Hong Kong（香港大学）
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）
