LLM Agent Skill Learning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

45 papers in the last four weeks, up 114% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 271

All topics

SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement
Jun 9, 2026Srishti Gautam, Arjun Radhakrishna, Sumit GulwaniLLM Self-Refinement LLM Agent Self-Improvement
Microsoft
TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning
Jun 9, 2026Mingyue Cheng, Shuo Yu, Daoyu Wang +5Multi-Agent LLM Systems LLM Agent Skill Learning
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
Jun 8, 2026Mingxian Lin, Shengju Qian, Yuqi Liu +9VLM Evaluation Game-Playing Agents
1The University of Hong Kong · 2LIGHTSPEED · 3The Chinese University of Hong Kong +1
What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents
Jun 8, 2026Qinghua Xing, Yinda Chen, Yaping Jin +6LLM Agent Skill Learning Agent Skill Learning
University of Science and Technology of China · 2Huawei Technologies · 3Tianjin University
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
Jun 8, 2026Haoran Sun, Wenjie Li, Yujie Zhang +8Continual Learning for LLM Agents LLM Agent Memory
1Fudan University · 2Shanghai Artificial Intelligence Laboratory · University of Science and Technology of China +1
Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
Jun 8, 2026Qianjun Pan, Yutao Yang, Junsong Li +5LLM Agent Memory LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory
Co-Evolving Skill Generation and Policy Optimization
Jun 7, 2026Zhiwei Zhang, Yudi Lin, Nikki Lijing Kuang +4LLM Agent Skill Learning RL for LLM Agents
The Pennsylvania State University · Nanyang Technological University · University of California, San Diego +2
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Jun 7, 2026Zhiwei Li, Yong HuContinual Learning for LLM Agents LLM Agent Skill Learning
WeChat AI, Tencent Inc., China · WeChat, Tencent Inc., China
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Jun 6, 2026Xiaojun Wu, Cehao Yang, Honghao Liu +7Agent Harness Optimization LLM Agent Workflow Optimization
1IDEA Research · 2The Hong Kong University of Science and Technology (Guangzhou) · 3DataArcTech Ltd.
VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation
Jun 6, 2026Jianhui Wei, Yan Zhang, Jie Tan +7Long Video Generation Agentic Video Generation
Zhejiang University · ByteDance
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Jun 5, 2026Chuan Xiao, Zhengbo Jiao, Shaobo Wang +5Software Engineering Agents LLM Agent Skill Learning
2Shanghai Jiao Tong University · 1AI Data, Alibaba Group
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
Jun 5, 2026Yuyang Zhang, Xinyuan Han, Xudong Jiang +1Agentic Workflows LLM Agent Skill Learning
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University · Nanchang University
OpenSkill: Open-World Self-Evolution for LLM Agents
Jun 4, 2026Zhiling Yan, Dingjie Song, Hanrong Zhang +8LLM Agent Skill Learning LLM Agent Verification
Lehigh University · University of Illinois Chicago · University of British Columbia +3
Unsupervised Skill Discovery for Agentic Data Analysis
Jun 4, 2026Zhisong Qiu, Kangqi Song, Shengwei Tang +4LLM Agent Skill Learning Agent Skill Learning
Zhejiang University · Ant Group
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Jun 4, 2026Aofan Yu, Chenyu Zhou, Tianyi Xu +8LLM Agent Skill Learning In-Context Learning
Shanghai Jiao Tong University · Sun Yat-Sen University · Shanghai Innovation Institute +1
SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization
Jun 4, 2026Qi Zhang, Zhaopeng Feng, Xiaonan Shi +8LLM Agent Self-Improvement LLM Agent Skill Learning
1Zhejiang University · 2Tongyi Lab · 3National University of Singapore
SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization
Jun 4, 2026Kuangshi Ai, Haichao Miao, Kaiyuan Tang +2Scientific Visualization Data Visualization
Univ. Notre Dame · LLNL
VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents
Jun 3, 2026Yunhao Yang, Neel P. Bhatt, Kevin Wang +3Robot Skill Learning Large Language Model-Based Robot Planning
1The University of Texas at Austin · 2Iowa State University
Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
Jun 3, 2026Bo Mao, Jie Zhou, Yutao Yang +5Lifelong Learning Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory · Software Engineering Institute, East China Normal University
Parthenon Law: A Self-Evolving Legal-Agent Framework
Jun 3, 2026Hejia Geng, Leo LiuLLM Agent Evaluation LLM Agent Self-Improvement
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
Jun 2, 2026Zherui Yang, Fan Liu, Yansong Ning +1Agentic RL LLM Agent Skill Learning
The Hong Kong University of Science and Technology (Guangzhou)
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
Jun 2, 2026Yuan Xiong, Ziqi Miao, Qian Chen +5Lifelong Learning Agents LLM Agent Skill Learning
1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · 3Shanghai Artificial Intelligence Laboratory, Shanghai, China · 4Beijing Academy of Artificial Intelligence, Beijing, China +1
FederatedSkill: Federated Learning for Agentic Skill Evolution
Jun 2, 2026Jingbo Yang, Guanyu Yao, Yang Zhang +3LLM Agent Self-Improvement LLM Agent Skill Learning
UC Santa Barbara · MIT-IBM Watson AI Lab · Cisco Research
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Jun 2, 2026Guhong Chen, Yingcheng Shi, Yongbin Li +6RL for Code Generation Agentic RL
1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · 2Tongyi Lab , Alibaba Group · 3Alibaba Group +1
Inducing Reasoning Primitives from Agent Traces
Jun 2, 2026Zhihan Lei, Jiarui Yan, Joshua Momo +1LLM Agent Skill Learning Agentic Reasoning
Carnegie Mellon University
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
Jun 1, 2026Zhongyu He, Yuanfan Li, Fei Huang +9LLM Agent Skill Learning Long-Horizon LLM Agents
Xiamen University · Meituan · Macao Polytechnic University
Unified Context Evolution for LLM Agents
Jun 1, 2026Zixuan Zhu, Yitong Hu, Yong Dai +4Continual Learning for LLM Agents LLM Agent Skill Learning
Nanyang Technological University · Beijing University of Posts and Telecommunications · Fudan University +4
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
Jun 1, 2026Xinyu Che, Junqi Xiong, Yunfei Ge +10Continual Learning for LLM Agents LLM Agent Skill Learning
Nanjing University · Kuaishou Technology
MetaForge: A Self-Evolving Multimodal Agent that Retrieves, Adapts, and Forges Tools On Demand
Jun 1, 2026Shouang Wei, Houcheng Min, Xinpeng Dong +8LLM Agent Skill Learning Multimodal Agents
East China Normal University · Zhejiang University · Tsinghua University +2
ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
Jun 1, 2026Zelin He, Haotian Lin, Boran Han +6Reinforcement Learning LLM Agent Skill Learning
The Pennsylvania State University · † Work done during an internship at Amazon · Amazon IntelliHub +1

Jun 9, 2026, cs.MAJ/K move · Enter open · S save

SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement

Srishti Gautam, Arjun Radhakrishna, Sumit Gulwani

Microsoft

LLM Self-Refinement LLM Agent Self-Improvement LLM Agent Skill Learning

Open paper AskPDF arXiv

Skill documents, structured natural-language instructions that guide Large Language Model (LLM) agents, are critical to modern agent frameworks, yet LLMs struggle to write skills that actually work. On SkillsBench, human-authored skills improve pass rates by 16.2 percentage points, while LLM-authored skills provide no measurable gain. We introduce SkillAxe, a fully unsupervised framework that enables LLMs to iteratively diagnose and refine their own skills. SkillAxe decomposes skill quality into four interpretable dimensions (quality impact, trigger precision, instruction compliance with fault attribution, and solution-path coverage), producing structured improvement briefs that require no ground-truth labels, test suites, or environment rewards. On SkillsBench, SkillAxe improves pass rates by 28% relative over unimproved LLM skills and closes 47--67% of the gap to human-authored skills. We validate the approach as a continuous improvement engine in the wild on SpreadsheetBench, where a SkillAxe-built skill library learns from past agent trajectories and raises pass rate from 16.0% to 52.0% using only 22 skills.

Momentum

Related topics

Latest papers 271