中文
相关论文

相关论文: The Art of Building Verifiers for Computer Use Age…

200 篇论文

Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically address. We show that a 1MB replay script that blindly executes a recorded action sequence…

Computer-using agents (CUAs) enable task completion through natural interaction with operating systems and software interfaces. While script-based verifiers are widely adopted for evaluation, they suffer from limited scalability and…

软件工程 · 计算机科学 2025-10-22 Haojia Lin , Xiaoyu Tan , Yulei Qin , Zihan Xu , Yuchen Shi , Zongyi Li , Gang Li , Shaofei Cai , Siqi Cai , Chaoyou Fu , Ke Li , Xing Sun

Computer-Use Agents (CUA) are becoming increasingly capable of autonomously operating digital environments through Graphical User Interfaces (GUI). Yet, most GUI remain designed primarily for humans--prioritizing aesthetics and…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Kevin Qinghong Lin , Siyuan Hu , Linjie Li , Zhengyuan Yang , Lijuan Wang , Philip Torr , Mike Zheng Shou

Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable…

Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and tool backends. In such settings, reliability isno longer…

计算与语言 · 计算机科学 2026-05-11 Zejian Chen , Zhanyuan Liu , Chaozhuo Li , Mengxiang Han , Songyang Liu , Litian Zhang , Feng Gao , Yiming Hei , Xi Zhang

Continual memory augmentation lets computer-using agents (CUAs) learn from prior interactions, but unvetted memories can encode domain-inappropriate or unsafe heuristics--spurious rules that drift from user intent and safety constraints. We…

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational…

计算与语言 · 计算机科学 2025-08-22 Jiuzhou Han , Wray Buntine , Ehsan Shareghi

Computer-Using Agents (CUAs) aim to autonomously operate computer systems to complete real-world tasks. However, existing agentic systems remain difficult to scale and lag behind human performance. A key limitation is the absence of…

We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection…

人工智能 · 计算机科学 2026-05-20 Jinbiao Wei , Qianran Ma , Yilun Zhao , Xiao Zhou , Kangqi Ni , Guo Gan , Arman Cohan

While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for…

To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…

TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a simple true-or-false classification task, the system identifies verifiable claims,…

Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs) but doing so remains a costly and time-intensive process. Prior work has used computer…

计算与语言 · 计算机科学 2026-04-30 Alice Gao , Weixi Tong , Rishab Vempati , Katharina Reinecke , R. Benjamin Shapiro , Tianyi Zhang , Jason Wu

Computer Use Agents (CUAs) are designed to autonomously operate digital interfaces, yet they often fail to reliably determine whether a given task has been completed. We present an autonomous evaluation and feedback framework that uses…

人工智能 · 计算机科学 2025-11-26 Marta Sumyk , Oleksandr Kosovan

Formal program verification is a longstanding goal in the field. We present the first quantitative comparison of the two primary compiler verification approaches, credible compilation/translation validation and full verification. Working…

编程语言 · 计算机科学 2026-05-12 Martin Rinard

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…

Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success of their trajectories, researchers have developed verifiers, such as LLM judges and…

机器学习 · 计算机科学 2026-05-29 Shuvom Sadhuka , Drew Prinster , Clara Fannjiang , Gabriele Scalia , Bonnie Berger , Aviv Regev , Hanchen Wang

Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These…

Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failures. While API-driven agents harness rich capabilities…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Yuhao Yang , Zhen Yang , Zi-Yi Dou , Anh Nguyen , Keen You , Omar Attia , Andrew Szot , Michael Feng , Ram Ramrakhya , Alexander Toshev , Chao Huang , Yinfei Yang , Zhe Gan

(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GUI agents, whose evaluation methods are susceptible to UI…

‹ 上一页 1 2 3 10 下一页 ›