Agent Skill Learning

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 123

All topics

ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
Oct 8, 2026Hongxing Li, Dingming Li, Yixin Li +6Agent Skill Learning Vision-Language Agents
Zhejiang University
Agentic-TTT: Training test-time policy for test-time training
Oct 8, 2026Jiahao Lu, Mohan KankanhalliTest-Time Training LLM Agent Self-Improvement
NUS AI Institute National University of Singapore
Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision
Oct 7, 2026Wenxi GanLearning from Demonstration Agent Skill Learning
City University of Hong Kong Shenzhen Loop Area Institute
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
Oct 7, 2026Yifei Lu, Cheng Liu, Dianzhi Yu +4LLM Agent Skill Learning Agent Skill Learning
Qiantang Credit, Hangzhou, China · Ant Group, Hangzhou, China · The Chinese University of Hong Kong
SkillSandbox: Skill Verification via Dynamic Scenario Synthesis
Oct 7, 2026Serin Kim, Kwangwook Seo, Dokyung Song +2Agent Skill Learning Self-Evolving Agents
Yonsei University
A self-learning scientific agent for X-ray diffraction
Oct 6, 2026Bin Cao, Huichi Zhou, Runyu Yang +7AI Agents for Scientific Discovery Materials Science
The Hong Kong University of Science and Technology (Guangzhou), China · University College London, United Kingdom · AI Lab, The Yangtze River Delta, China +1
Is this machine playing?
Oct 5, 2026Nathan Cloos, Antonio Norelli, Daniel Durbin +3Agent Skill Learning Self-Improving Agents
MIT
Mining Agent Skills from Production Traces
Oct 5, 2026Yue Ran Kang, Colton Mikolajczyk, Chhaya Methani +4LLM Agents Agent Skill Learning
Massachusetts Institute of Technology · Microsoft Corporation
TeleTune: Evolving Agent Skills From Offline Telemetry
Oct 4, 2026Justin Chih-Yao Chen, Elias Stengel-Eskin, Yan Chen +6Computer-Use Agents LLM Agent Skill Learning
UNC Chapel Hill · Microsoft
Learning Transferable Skills using Goal-Conditioned Bisimulation
Sep 30, 2026Mohammad Amin Abbasfar, Farbod Azimmohseni, Mohammad Hossein RohbanAgent Skill Learning Trajectory Representation Learning
Department of Computer Engineering Sharif University of Technology
Game-Guided Skill Discovery through Self-Play for Playable Agent Control
Sep 30, 2026Seungeun Rho, Jeonghwan Kim, Xue Bin Peng +1Robot Skill Learning Hierarchical RL
Georgia Institute of Technology · Simon Fraser University and NVIDIA
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Sep 30, 2026Kaixing Zhang, Changming Li, Yingdong Shi +5LLM Agent Self-Improvement LLM Agent Skill Learning
ShanghaiTech University · Meituan
Do Self-Evolving Skills Generalize to Held-Out Tasks?
Sep 30, 2026Xihao Piao, Zifeng Wang, Zhen ChenAgent Skill Learning Self-Evolving Agents
SANKEN, Osaka University
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
Sep 29, 2026Mingda Zhang, Hanwen Zhang, Qiang Huang +5Multi-Agent Orchestration Agent Skill Learning
The Chinese University of Hong Kong, Shenzhen, China · Dalian University of Technology, China · Fudan University, China +3
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
Sep 29, 2026Jaewon Chu, Ji Soo Lee, Jihwan Park +8LLM Agent Skill Retrieval Agent Skill Learning
Korea University · KAIST · Meta AI
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
Sep 29, 2026Sicheng Xie, Yitong Chen, Haidong Cao +3Robot Skill Learning Agent Skill Learning
Institute of Trustworthy Embodied AI, Fudan University · Shanghai Innovation Institute · NeoteAI.
SkillCome: Group Contrast Skill Optimization with Dual Memory
Sep 29, 2026Haolin Li, Feng Hong, Ang Li +6Large Language Model-Guided Optimization LLM Agent Skill Learning
Fudan University · Ant Group · Shanghai Jiao Tong University
From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis
Sep 28, 2026Longxiao Fan, Tao Zhang, Han Yan +5LLM-Based Program Synthesis Agent Skill Learning
Fudan University · University of Science and Technology of China · Huawei Technologies Ltd.
ARISE: Adapting to Evolving Capability Gaps in Agentic Reinforcement Learning
Sep 28, 2026Kun Feng, Yuchen Fang, Yiyang Tan +6Agentic RL Long-Horizon Agent Evaluation
ShanghaiTech University · Ant Group
V-Gym: Enhancing Agentic Visual Reasoning via Skill-Data Co-Evolution
Sep 28, 2026Bei Yan, Yuecong Min, Jie Zhang +3Synthetic Data Generation Multimodal Reasoning
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
SkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents
Sep 28, 2026Bingqing Jiang, Guoxi Zhang, Jasper Wang +7Multimodal Reward Modeling Rubric-Based RL
The University of Hong Kong · WeChat, Tencent · Peking University +2
Evo2Team: When Do Evolved Skills Transfer? From Selection to Deployment
Sep 28, 2026Renxiang Wang, Jiaming CuiMulti-Agent Coordination Task Transferability Estimation
Virginia Tech, Blacksburg, VA
R $^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution
Sep 27, 2026Mingda Zhang, Qiang Huang, Yanjin Li +4LLM Agent Self-Improvement Generative Flow Networks
The Chinese University of Hong Kong, Shenzhen · Fudan University · University of Illinois at Urbana-Champaign +2
SIVIA-RSI: Source-Grounded Adaptation of Diagramming Skills
Sep 27, 2026Feng Yuan, Yifan Gao, Haoyue Li +1Cross-Domain Transfer Learning Agent Skill Learning
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
CORTEX: A Verified Experience Layer for Generalist Agents
Sep 27, 2026Garapati Keerthana, Manik GuptaAI Agent Reliability Lifelong Learning Agents
Birla Institute of Technology and Science, Pilani, Hyderabad, India
Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents
Sep 25, 2026Yiran Hu, Nan Jiang, Shanchao Liang +3Coding Agents Cost-Aware Inference
Purdue University
Towards Strategy-Level RSI for Skill-Augmented Agents: Learning When to Reuse Skills from Execution Feedback
Sep 22, 2026Shuang Guo, Xiaobo Sui, Fei Jiang +4LLM Agent Skill Retrieval LLM Agents
Central China Normal University
TTSE: A Two-Track Online Self-Evolution Framework
Sep 21, 2026Ruimin Pei, Yongkang Wu, Shangyi Zheng +5LLM Agent Self-Improvement Agent Skill Learning
Poisson Lab, Huawei China
DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery
Sep 15, 2026Sun Woo Kim, Xue Bin PengRobot Skill Learning Humanoid Robot Control
Simon Fraser University, Canada · NVIDIA, Canada
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents
Sep 15, 2026Bofan Chen, Boxuan Zhang, Fei Tang +7Mobile GUI Automation GUI Agents
Zhejiang University · UESTC

Oct 8, 2026, cs.CVJ/K move · Enter open · S save

ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills

Hongxing Li, Dingming Li, Yixin Li, Yong Du+5

Zhejiang University

Agent Skill Learning Vision-Language Agents RL for VLMs

Open paper AskPDF arXiv

Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies. Yet most existing approaches remain text-centric, linearizing spatial layouts and action-state correspondences into language that loses critical geometric structure. Recent efforts have begun incorporating visual evidence, but construct and update skills separately from policy optimization, leaving their mutual improvement underexplored. We propose ViSkill, a visual-native skill learning framework that encodes successful interactions as composite visual skill cards directly accessible to VLM agents. Retrieved skills guide both inference and reward shaping, while successful trajectories are distilled back into the library, forming a closed feedback loop in which skill accumulation and policy improvement reinforce each other. An optional cold-start mechanism further accelerates early-stage learning. Evaluated on Sokoban, FrozenLake, and PrimitiveSkill, ViSkill achieves an overall success rate of 0.89, rising to 0.91 with cold-start initialization, outperforming all evaluated proprietary and open-source baselines while converging faster than standard PPO. Our code is available at https://github.com/ZJU-REAL/ViSkill.

Momentum

Related topics

Latest papers 123