Skills

Ask about this topic

Momentum

30 papers in the last four weeks, down 43% on the four weeks before. 0.4% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 334

All topics
CardsList

  1. Same Reward, Different Skills: When Multimodal RL Learns to Look

    Oct 1, 2026Haocun Ye, Xinlong Jiang, Qile Chen +6Multimodal Reasoning BenchmarksVisual Evidence

    University of the Chinese Academy of Sciences · Institute of Computing Technology, Chinese Academy of Sciences · Independent Researcher

  2. Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills

    Oct 1, 2026Ngoc Phuoc An Vo, Aarya Doshi, Vadim SheininAgentic EvaluationsReusable Agent Skills

    IBM · Georgia Institute of Technology · IBM Research

  3. SkillEvoLean: Mutation-enhanced skill evolution for Lean provers

    Oct 1, 2026Kuo Zhou, ZiXion Yang, Lu ZhangSkill EvolutionTheorem Proving

    Peking University

  4. Chaining Skills to Hijack LLM Agents

    Oct 1, 2026Tian Dong, Zixuan Ma, Haodong Zhao +3AttackerAdversarial Robustness

    The University of Hong Kong · Shandong University · Shanghai Jiao Tong University +1

  5. MCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent Skills

    Oct 1, 2026Zongrui Yang, Li Xintong, Runchen Xu +4SkillsAgentic Evaluations

  6. MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending

    Oct 1, 2026Yifan Hu, Luhang Hong, Mingkang Long +5Full-Body Humanoid ControlHumanoid Loco-Manipulation

    Nanyang Technological University · Southeast University · Purple Mountain Laboratories

  7. SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization

    Sep 30, 2026Huancheng Chen, Xiaodi Sun, Zhaoqiong Huang +2Self-Evolving Skill LibrariesSkills

    Microsoft AI

  8. Learning Transferable Skills using Goal-Conditioned Bisimulation

    Sep 30, 2026Mohammad Amin Abbasfar, Farbod Azimmohseni, Mohammad Hossein RohbanUnsupervised Skill DiscoverySkills

    Department of Computer Engineering Sharif University of Technology

  9. Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs

    Sep 30, 2026Taegeun Yang, Youngju Na, Yoonki Cho +1Photometric SupervisionCompositional Generalization

    Korea Advanced Institute of Science and Technology (KAIST)

  10. Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents

    Sep 30, 2026Tobias Kaisar, Aritra DharMalicious AgentsAttacker Large Language Model

    Computing System Labs, Huawei Research Zurich

  11. ActionGuard: Tool Call Authorization under Poisoned Skills

    Sep 30, 2026Jihun Han, Yejin Jang, Byung Il Kwak +1Tool InvocationAuthorization

    Korea University Republic of Korea

  12. SkillFM: Generating Skills for LLM Agents via Latent Flow Matching

    Sep 30, 2026Zuming Zhang, Jie He, Yizhe Zhang +1SkillsLarge Language Model Agents

    Nanyang Technological University · University of Edinburgh · Meta

  13. Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents

    Sep 30, 2026Kaixing Zhang, Changming Li, Yingdong Shi +5Skill EvolutionSelf-Evolution

    ShanghaiTech University · Meituan

  14. Do Self-Evolving Skills Generalize to Held-Out Tasks?

    Sep 30, 2026Xihao Piao, Zifeng Wang, Zhen ChenSkill EvolutionSkills

    SANKEN, Osaka University

  15. SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale

    Sep 30, 2026Guanqun Yang, Wenlong Zhang, Tian Shi +1Agent Skill RetrievalSkills

    Stevens Institute of Technology, Hoboken, NJ, USA · Independent Researcher

  16. Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation

    Sep 29, 2026Jaewon Chu, Ji Soo Lee, Jihwan Park +8SkillsAgentic Optimization

    Korea University · KAIST · Meta AI

  17. Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

    Sep 29, 2026Sicheng Xie, Yitong Chen, Haidong Cao +3Human-To-Robot TransferEmbodied Agents

    Institute of Trustworthy Embodied AI, Fudan University · Shanghai Innovation Institute · NeoteAI.

  18. EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation

    Sep 29, 2026Jin Chen, Yiming Jiang, Chongyang Xu +8Human-To-Robot TransferHumanoid Loco-Manipulation

    OpenDriveLab at The University of Hong Kong · Alibaba Group · Shanghai Innovation Institute +4

  19. SkillCome: Group Contrast Skill Optimization with Dual Memory

    Sep 29, 2026Haolin Li, Feng Hong, Ang Li +6SkillsLarge Language Model Agents

    Fudan University · Ant Group · Shanghai Jiao Tong University

  20. Real2Gym: Building Gyms from Videos, Bringing Skills to Robots

    Sep 29, 2026Kerui Ren, Yingxiang Xu, Kaiwen Song +4Robotic SystemsRobot Systems

    Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Zhejiang University +3

  21. SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs

    Sep 29, 2026Haoran Ou, Gelei Deng, Xuanye Zhang +3Malicious AgentsSkills

    Nanyang Technological University

  22. SAKI: Skill Assembly and Kinematic Imitation from Human Videos for Long-Horizon Mobile Manipulation

    Sep 28, 2026Yijie Lu, James Zhao, Weiming ZhiHuman-To-Robot TransferMotion Imitation

    School of Computer Science, The University of Sydney, Australia · Australian Centre for Robotics, The University of Sydney, Australia

  23. Report: Progressive Disclosure of Agent Skills

    Sep 28, 2026Guilin Zhang, Kai Zhao, Priyanka Mudgal +4SkillsAgentic Workflows

    Workday AI Research

  24. PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents

    Sep 28, 2026Lucas Biechy, Cédric Eichler, Héber H. Arcolezi +1PrivacyLarge Language Model Agents

    Petscraft, Inria · Université Paris-Saclay · INSA CVL +3

  25. RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents

    Sep 28, 2026Hao Li, Hangfan Zhang, Zhiyao Cui +5Large Language Model RoutingInference Cost

    Shanghai Artificial Intelligence Laboratory · Northwestern Polytechnical University

  26. SkillFocus: Evolving Agent Skills via Capability Decomposition

    Sep 28, 2026Ning Wang, Zhiren Gong, Bingdong Li +2Self-Evolving Skill LibrariesSkills

    East China Normal University · Nanyang Technological University · Southern University of Science and Technology +1

  27. SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering

    Sep 28, 2026Yanwei Huang, Mingxuan Zhu, Shujie Li +3Text-To-Video Generation ModelSelf-Evolving Skill Libraries

    HKUST · KlingAI · Shanghai Jiaotong University +1

  28. Evo2Team: When Do Evolved Skills Transfer? From Selection to Deployment

    Sep 28, 2026Renxiang Wang, Jiaming CuiSkillsCross-Task Knowledge Transfer

    Virginia Tech, Blacksburg, VA

  29. R2^2 Flow: Recursive Self-Improvement via Recursive Skill Evolution

    Sep 27, 2026Mingda Zhang, Qiang Huang, Yanjin Li +4Skill EvolutionRecursive Self-Improvement

    The Chinese University of Hong Kong, Shenzhen · Fudan University · University of Illinois at Urbana-Champaign +2

  30. Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents

    Sep 27, 2026Weiyi Xu, Xiaowen Yang, Wen Da +7Synthetic EnvironmentsSkills

    AllSpark Team

  31. SIVIA-RSI: Source-Grounded Adaptation of Diagramming Skills

    Sep 27, 2026Feng Yuan, Yifan Gao, Haoyue Li +1DiagramsSkills

    School of Biomedical Engineering (Suzhou), Division of Life Science and Medicine, University of Science and Technology of China, Hefei, China · Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China · Shanghai Innovation Institute, Shanghai, China

  32. What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review

    Sep 27, 2026Shuyang ZhangAgentic EvaluationsSkills

    The Hong Kong Polytechnic University, Hong Kong, China

  33. SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

    Sep 23, 2026Zhilong Ge, Yuting Shao, Yutao Yang +6Reusable Agent SkillsSkills

    School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory

  34. SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence

    Sep 22, 2026Shuang GuoSkillsLarge Language Model Agents

    Central China Normal University

  35. Skill Sequence Planning for Collaborative Multi-Robot Construction

    Sep 22, 2026Xi Wang, Bo Fu, Carol C. Menassa +2ConstructionCollision-Free Trajectories

    Department of Construction Science, Texas A&M University, College Station, TX 77843, USA · Amazon Robotics, North Reading, MA 01864, USA · Department of Civil and Environmental Engineering, University of Michigan, MI 48109, USA +1

  36. Making Agents More Consistent: Skills Should Form Habits for Repeat Tasks

    Sep 21, 2026Travis Weber, Rohit TanejaReusable Agent SkillsSkills

    Pheo Inc

  37. MimicAgent: Quadruped Skills via Prompt-to-Trajectory Generation

    Sep 21, 2026Lucky Kant Nayak, Narayanan Palghat Parameswaran, Neehar Peri +1MimicSkills

    Carnegie Mellon University

  38. FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA

    Sep 17, 2026Yanzhang Ma, Zhenghan Tai, Hanwei Wu +25Financial Question AnsweringRecursive Self-Improvement

    University of Toronto · McMaster University · University of California, Los Angeles +11

  39. RAUL: Reference-Assisted Ureteroscopy Localization for Skill Assessment

    Sep 16, 2026Fangjie Li, Mai Bui, Charan Mohan +4Robotic Soft EsophagusLocalization

    Department of Biomedical Engineering, Vanderbilt University, Nashville, TN 37240 USA · Department of Computer Science, Vanderbilt University, Nashville, TN 37240 USA · Department of Urology, Vanderbilt University Medical Center, Nashville, TN 37232 USA

  40. Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

    Sep 15, 2026Bofan Chen, Boxuan Zhang, Fei Tang +7Graphical User Interface AgentsGraphical User Interface

    Zhejiang University · UESTC

  41. After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem

    Sep 15, 2026Yunpeng Xiong, Ting ZhangOpenclawReusable Agent Skills

    Monash University, Australia

  42. The Router Within: Eliciting Native Skill Routing from a Frozen LLM

    Sep 14, 2026Ruishuo Chen, Xun Wang, Yu Chen +2SkillsLarge Language Model Routing

    Institute for Interdisciplinary Information Sciences, Tsinghua University

  43. RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language Agents

    Sep 14, 2026Mengyi Deng, Xin Li, Duyi Pan +4RepairMultilingual Agents

    1Information Hub, The Hong Kong University of Science and Technology (Guangzhou), China · 2The Hong Kong University of Science and Technology, Hong Kong SAR

  44. SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution

    Sep 14, 2026Haoxiang Kang, Ming WenSkill EvolutionSkills

    1Independent Researcher · 2Fudan University

  45. One Skill Does Not Fit All: Automatic Discovery and Taxonomy-Guided Routing of Frame-Selection Skills for Long-Video Question Answering

    Sep 14, 2026Jian Hu, Zixu Cheng, Da Li +3Long Video Question AnsweringSkills

    Queen Mary University of London · Samsung AI Research Institute · Nanyang Technological University, Singapore

  46. Skill Issue: Lessons from Optimizing Repository SKILLs for Coding Agents

    Sep 14, 2026Mykhailo Kozyrev, Andrei Kozyrev, Anton PodkopaevRepository-Level Code UnderstandingCoding Agents

    Technical University of Munich, JetBrains Research Munich, Germany · JetBrains Research Berlin, Germany · Constructor University Bremen, JetBrains Research Amsterdam, Netherlands

  47. When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents

    Sep 12, 2026Syed Shariyar Murtaza, Yifan Nie, Utkarsh Soni +2Synthetic Training DataSkills

    Manulife, 200 Bloor St E, Toronto, ON M4W 1E5, Canada

  48. Dynamical Non-compensatory Multidimensional IRT Model Using Variational Approximation

    Sep 9, 2026Hiroshi Tamano, Daichi MochihashiItem Response TheoryKullback-Leibler Divergence

    the graduate university for advanced studies, sokendai · the institute of statistical mathematics

  49. InstantMimic: A High Performance System for Learning Physics-based Skills in Seconds

    Sep 9, 2026Ikjun Choi, Geonho Leem, Jungdam WonMimicSkills

    Seoul National University, Seoul, South Korea

  50. GTA-2: A Multi-VLM Framework for Synthesizing Robot Manipulation Skills via Grounded Task Axes

    Sep 9, 2026M. Yunus Seker, Shobhit Aggarwal, Ruwan Wickramarachchi +2Skills

    The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA · Bosch Research, Pittsburgh, PA, USA

  51. SkillAdam: Stable and Efficient Skill Evolution for Agents

    Sep 8, 2026Gaoyuan Li, Meihao Fan, Yizhe Liu +7Skill EvolutionSkills

    Renmin University of China · Tencent

  52. SkillAlign: Aligning Skill Interfaces for LLM-based Agents

    Sep 7, 2026Shuo Ren, Xiaomian Kang, Jiajun ZhangSkillsExposure

    Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Wuhan AI Research

  53. Toward anIntegrated Cognitive--Ergonomic Architecture forHuman--Machine Interaction: Combining Cognitive Models with~Human Factors Ergonomics

    Sep 3, 2026Antoine Lenat, Olivier Cheminat, Damien Chablat +1Human-Centered FrameworkCognitive Science

    Cetim, LS2N, LS2N - équipe RoMas, LS2N - équipe PACCE · Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004 44000 Nantes, France · CETIM, 74 Route de la Jonelière, 44300 Nantes +4

  54. Programming and execution of skill-based human-robot-crane collaborative tasks

    Sep 3, 2026Taneli Lohi, Markku Suomalainen, Roope Mellanen +1Human-Robot CollaborationHuman-To-Robot Transfer

    Intelligent Robotics VTT Technical Research Centre of Finland Ltd Oulu, Finland · Konecranes oyj. Hyvinkää, Finland

  55. Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

    Sep 1, 2026Jinhu Qi, Minda Hu, Wentao Zhang +4In-Context LearningSkills

    The Chinese University of Hong Kong · Macao Polytechnic University · Xi’an Jiaotong University +1

  56. Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents

    Sep 1, 2026Seonghyeon Cho, Chanjun ParkSkills

    Soongsil University

  57. Autonomously Acquiring Robot Manipulation Skills with Language-Driven Quality-Diversity

    Aug 31, 2026Émiland Garrabé, Mahdi Khoramshahi, Stéphane DoncieuxMotion PrimitivesRobot Systems

    ISIR, Sorbonne Universit´e, France

  58. SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents

    Aug 31, 2026Xiaofan Bai, Chao Liu, Hongqiang Lin +5Unsupervised Skill DiscoveryData Compression Methods

    1Alibaba Group · 2Zhejiang University · †Project leader

  59. Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

    Aug 30, 2026Wujie Xiong, Rabimba Karanjai, Yang Lu +2LLM Defense MechanismsLarge Language Model Agents

    Kent State Univeristy · PayPal AI Labs · University of Houston

  60. Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents

    Aug 30, 2026Timothy Kassis, Vinayak Agarwal, Yuhuan He +2Reusable Agent SkillsScientific Workflows

    K-Dense, Inc.