English
Related papers

Related papers: Skill1: Unified Evolution of Skill-Augmented Agent…

200 papers

While large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typically treat these two evolutionary processes in isolation.…

Computation and Language · Computer Science 2026-04-14 Zihao Cheng , Zeming Liu , Yingyu Shan , Xinyi Wang , Xiangrong Zhu , Yunpu Ma , Hongru Wang , Yuhang Guo , Wei Lin , Yunhong Wang

The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies…

Artificial Intelligence · Computer Science 2026-03-20 Yu Li , Rui Miao , Zhengling Qi , Tian Lan

Model collaboration -- systems where multiple language models (LMs) collaborate -- combines the strengths of diverse models with cost in loading multiple LMs. We improve efficiency while preserving the strengths of collaboration by…

Computation and Language · Computer Science 2026-02-25 Shangbin Feng , Kishan Panaganti , Yulia Tsvetkov , Wenhao Yu

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Robotics · Computer Science 2024-08-19 Xufeng Zhao , Cornelius Weber , Stefan Wermter

Large language models (LLMs) have recently been used for sequential decision making in interactive environments. However, leveraging environment reward signals for continual LLM actor improvement is not straightforward. We propose Skill Set…

Machine Learning · Computer Science 2024-06-25 Kolby Nottingham , Bodhisattwa Prasad Majumder , Bhavana Dalvi Mishra , Sameer Singh , Peter Clark , Roy Fox

Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rules, or auxiliary…

Artificial Intelligence · Computer Science 2026-05-13 Min Yang , Jinghua Piao , Xu Xia , Xiaochong Lan , Jiaju Chen , Yongshun Gong , Yong Li

Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…

Artificial Intelligence · Computer Science 2018-02-27 Evan Zheran Liu , Kelvin Guu , Panupong Pasupat , Tianlin Shi , Percy Liang

Modern scientific ecosystems are rich in procedural knowledge across repositories, APIs, scripts, notebooks, documentation, databases, and papers, yet much of this knowledge remains fragmented across heterogeneous artifacts that agents…

Artificial Intelligence · Computer Science 2026-04-07 Shuaike Shen , Wenduo Cheng , Mingqian Ma , Alistair Turcan , Martin Jinye Zhang , Jian Ma

Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work. However, performance degrades…

Software Engineering · Computer Science 2026-05-26 Hongwen Song , Song , Wei

LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for…

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a…

Artificial Intelligence · Computer Science 2026-05-26 Songjun Tu , Chengdong Xu , Qichao Zhang , Yaocheng Zhang , Xiangyuan Lan , Linjing Li , Dong Li , Dongbin Zhao

Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them…

Computation and Language · Computer Science 2026-05-26 Haozhen Zhang , Quanyu Long , Jianzhu Bao , Tao Feng , Weizhi Zhang , Haodong Yue , Wenya Wang

Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on…

Machine Learning · Computer Science 2020-10-23 Karl Pertsch , Youngwoon Lee , Joseph J. Lim

Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills over many timesteps, and robust decision making under delayed…

Artificial Intelligence · Computer Science 2026-04-24 Xiyang Wu , Zongxia Li , Guangyao Shi , Alexander Duffy , Tyler Marques , Matthew Lyle Olson , Tianyi Zhou , Dinesh Manocha

In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or avoiding overly technical wording, yet such interaction experience…

Artificial Intelligence · Computer Science 2026-03-06 Yutao Yang , Junsong Li , Qianjun Pan , Bihao Zhan , Yuxuan Cai , Lin Du , Jie Zhou , Kai Chen , Qin Chen , Xin Li , Bo Zhang , Liang He

Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is…

Machine Learning · Computer Science 2026-05-18 Zhengxi Lu , Zhiyuan Yao , Jinyang Wu , Chengcheng Han , Qi Gu , Xunliang Cai , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

Skills are essential for unlocking higher levels of problem solving. A common approach to discovering these skills is to learn ones that reliably reach different states, thus empowering the agent to control its environment. However,…

Machine Learning · Computer Science 2025-10-07 Jonathan Colaço Carr , Qinyi Sun , Cameron Allen

Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…

Machine Learning · Computer Science 2026-03-19 Dilxat Muhtar , Jiashun Liu , Wei Gao , Weixun Wang , Shaopan Xiong , Ju Huang , Siran Yang , Wenbo Su , Jiamang Wang , Ling Pan , Bo Zheng

Structured skill prompts improve exploration in long-horizon agentic reinforcement learning (RL). Skill-augmented RL methods retain external skills at inference, while skill-internalization RL methods withdraw them during training to enable…

Artificial Intelligence · Computer Science 2026-05-28 Hongxiang Lin , Zhirui Kuai , Erpeng Xue , Lei Wang

Multi-agent systems (MAS) tackle complex tasks by distributing expertise, though this often comes at the cost of heavy coordination overhead, context fragmentation, and brittle phase ordering. Distilling a MAS into a single-agent skill can…

Artificial Intelligence · Computer Science 2026-04-27 Binyan Xu , Dong Fang , Haitao Li , Kehuan Zhang