English
Related papers

Related papers: OSExpert: Computer-Use Agents Learning Professiona…

200 papers

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

Artificial Intelligence · Computer Science 2026-05-26 Erhan Zhang , Yiqun Chen , Zechun Niu , Wei Yang , Xiaochi Wei , Yan Gao , Yi Wu , Yao Hu , Jiaxin Mao

Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and…

Computation and Language · Computer Science 2026-04-20 Chiwei Zhu , Benfeng Xu , Mingxuan Du , Shaohan Wang , Xiaorui Wang , Zhendong Mao , Yongdong Zhang

The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill…

Computation and Language · Computer Science 2026-03-03 Hao Li , Chunjiang Mu , Jianhao Chen , Siyue Ren , Zhiyao Cui , Yiqun Zhang , Lei Bai , Shuyue Hu

The process of scientific discovery relies on an interplay of observations, analysis, and hypothesis generation. Machine learning is increasingly being adopted to address individual aspects of this process. However, it remains an open…

Artificial Intelligence · Computer Science 2026-05-26 Maximilian Nägele , Florian Marquardt

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks…

Information exploration tasks are inherently complex, ill-structured, and involve sequences of actions usually spread over many sessions. When exploring a dataset, users tend to experiment higher degrees of uncertainty, mostly raised by…

Human-Computer Interaction · Computer Science 2022-10-03 Thiago Nunes , Daniel Schwabe

The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common approaches, but current methods have considerable…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

Edge computing breaks with traditional autoscaling due to strict resource constraints, thus, motivating more flexible scaling behaviors using multiple elasticity dimensions. This work introduces an agent-based autoscaling framework that…

Artificial Intelligence · Computer Science 2026-01-13 Boris Sedlak , Alireza Furutanpey , Zihang Wang , Víctor Casamayor Pujol , Schahram Dustdar

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…

Computation and Language · Computer Science 2025-10-14 Sabrina McCallum , Amit Parekh , Alessandro Suglia

We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control. We experiment with multiple evaluation models that trade off between inference cost, modularity of…

Artificial Intelligence · Computer Science 2024-10-08 Jiayi Pan , Yichi Zhang , Nicholas Tomlin , Yifei Zhou , Sergey Levine , Alane Suhr

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

Information Retrieval · Computer Science 2026-05-27 Yingli Zhou , Wang Shu , Yaodong Su , Wenchuan Du , Yixiang Fang , Xuemin Lin

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Machine Learning · Computer Science 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi

Long-horizon, repetitive workflows are common in professional settings, such as processing expense reports from receipts and entering student grades from exam papers. These tasks are often tedious for humans since they can extend to extreme…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jing Wu , Daphne Barretto , Yiye Chen , Nicholas Gydé , Yanan Jian , Yuhang He , Vibhav Vineet

One of the fundamental problems in digital agents is their lack of understanding of their environment. For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To…

Computation and Language · Computer Science 2026-03-04 Apurva Gandhi , Graham Neubig

When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from non-expert humans. We argue that the robot should…

Robotics · Computer Science 2020-11-10 Pamela Carreno-Medrano , Stephen L. Smith , Dana Kulic

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain…

While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between…

Computation and Language · Computer Science 2026-05-27 Haoyi Hu , Qirong Lyu , Xianghan Kong , Weiwen Liu , Jianghao Lin , Zixuan Guo , Yan Xu , Yasheng Wang , Weinan Zhang , Yong Yu

Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a…

Artificial Intelligence · Computer Science 2026-02-04 Zhen Wang , Fan Bai , Zhongyan Luo , Jinyan Su , Kaiser Sun , Xinle Yu , Jieyuan Liu , Kun Zhou , Claire Cardie , Mark Dredze , Eric P. Xing , Zhiting Hu

Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution…

Computation and Language · Computer Science 2024-06-25 Zhengliang Shi , Shen Gao , Xiuyi Chen , Yue Feng , Lingyong Yan , Haibo Shi , Dawei Yin , Pengjie Ren , Suzan Verberne , Zhaochun Ren