English
Related papers

Related papers: SkillEvolver: Skill Learning as a Meta-Skill

200 papers

Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-agent system (MAS) restructuring. This separation can create…

Multiagent Systems · Computer Science 2026-05-19 Shuai Pan , Yixiang Liu , Jiaye Gao , Te Gao , Weiwen Liu , Jianghao Lin , Zhihui Fu , Jun Wang , Weinan Zhang , Yong Yu

Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously navigate, edit, and test complex repositories. While…

Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…

Artificial Intelligence · Computer Science 2026-03-25 Raj Ghugare , Roger Creus Castanyer , Catherine Ji , Kathryn Wantlin , Jin Schofield , Karthik Narasimhan , Benjamin Eysenbach

Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and updated, while paying less attention to how experience should…

Computation and Language · Computer Science 2026-05-11 Weixiang Zhao , Yingshuo Wang , Yichen Zhang , Yanyan Zhao , Yu Zhang , Yang Wu , Dandan Tu , Bing Qin , Ting Liu

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach…

Artificial Intelligence · Computer Science 2023-02-08 Rundong Wang , Longtao Zheng , Wei Qiu , Bowei He , Bo An , Zinovi Rabinovich , Yujing Hu , Yingfeng Chen , Tangjie Lv , Changjie Fan

This technical report presents SkillTester, a tool for evaluating the utility and security of agent skills. Its evaluation framework combines paired baseline and with-skill execution conditions with a separate security probe suite. Grounded…

Cryptography and Security · Computer Science 2026-04-01 Leye Wang , Zixing Wang , Anjie Xu

AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…

Human-Computer Interaction · Computer Science 2026-01-27 Yimeng Liu , Misha Sra , Jeevana Priya Inala , Chenglong Wang

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task…

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…

Machine Learning · Computer Science 2023-12-05 Haoqi Yuan , Chi Zhang , Hongcheng Wang , Feiyang Xie , Penglin Cai , Hao Dong , Zongqing Lu

Recently, there have been several high-profile achievements of agents learning to play games against humans and beat them. In this paper, we study the problem of training intelligent agents in service of game development. Unlike the agents…

Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by setting and pursuing…

Machine Learning · Computer Science 2026-01-28 Octavio Pappalardo

Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…

Artificial Intelligence · Computer Science 2026-02-23 Yangjie Xu , Lujun Li , Lama Sleem , Niccolo Gentile , Yewei Song , Yiqun Wang , Siming Ji , Wenbo Wu , Radu State

Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of…

Artificial Intelligence · Computer Science 2025-12-10 Antonio Terpin , Raffaello D'Andrea

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. One promising approach is…

Artificial Intelligence · Computer Science 2026-03-11 Jiongxiao Wang , Qiaojing Yan , Yawei Wang , Yijun Tian , Soumya Smruti Mishra , Zhichao Xu , Megha Gandhi , Panpan Xu , Lin Lee Cheong

While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agent performance increasingly plateaus due to the quality of the tool interfaces these agents…

Artificial Intelligence · Computer Science 2026-04-30 Ruocheng Guo , Kaiwen Dong , Xiang Gao , Kamalika Das

Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Juncheng Li , Xin Wang , Siliang Tang , Haizhou Shi , Fei Wu , Yueting Zhuang , William Yang Wang

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic systems question: how long does an agent remain reliable after…

Artificial Intelligence · Computer Science 2026-05-27 Jianing Zhu , Yeonju Ro , John Robertson , Kevin Wang , Junbo Li , Haris Vikalo , Aditya Akella , Zhangyang Wang

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw (228,000 GitHub stars) and Anthropic Agent Skills (75,600 stars) -- has introduced a critical supply chain attack surface. The ClawHavoc campaign…

Cryptography and Security · Computer Science 2026-03-03 Varun Pratap Bhardwaj

While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible. To mitigate this issue,…

Machine Learning · Computer Science 2022-04-26 Taewook Nam , Shao-Hua Sun , Karl Pertsch , Sung Ju Hwang , Joseph J Lim