arXiv AI

ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks

ChainWorld is a new benchmark that composes atomic OSWorld tasks into long‑horizon desktop workloads, creating 347 chains of length two to four that compare two renderings of the same task sequence. In single‑turn evaluation all tasks are presented together in one prompt, while in multi‑turn evaluation tasks are revealed one at a time. Across four current computer‑use agents, maximum chain completion is 31 %, with multi‑turn evaluation improving completion for three models but both protocols remaining challenging and exposing different failure profiles.

arXiv AI

Aug 20

ComponentBench: Diagnosing Component-Level Failures in Computer-Use Agents

ComponentBench is a new benchmark that evaluates computer‑use agents at the component level on modern web UIs. It contains 97 canonical UI components and 2,910 programmatically verified tasks, along with cleaned human reference trajectories for measuring task success and interaction efficiency. The benchmark also offers a scalable pipeline for auditing structural difficulty and synthesizing failure analyses across tasks and component families.

By Tianchen Guan, Xinlei Lin, Royce Cheng-Yue, Xiangjun Wang, Shuyan Zhou

llms agents benchmarks

arXiv AI

Jul 28

Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents

arXiv:2607. 22689v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are systems powered by large multimodal models (LMMs).

By Zedong Yu, Qianxing Li, Zhi Gao, Liuyu Xiang, Chenrui Shi, Yang Liu, Huiming Wu, Yujie Wei, Yuhao Fei, Yubo Fu, Zhaofeng He

llms agents multimodal benchmarks

arXiv AI

Jun 3

DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration

arXiv:2606. 03103v1 Announce Type: new Abstract: Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses.

By Wenkai Wang, Tao Xiong, Jingchen Ni, Yunpeng Bao, Xiyun Li, Tianqi Liu, Hongcan Guo, Zilong Huang, Shengyu Zhang

llms agents benchmarks

arXiv AI

Jun 9

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

arXiv:2606. 09426v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools.

By Wanli Li, Bowen Zhou, Yunyao Yu, Zhou Xu, Yifan Yang, Dongsheng Li, Caihua Shan

agents benchmarks

arXiv Machine Learning

Sep 22

OSWorld-Pro: Process-based Evaluation for Computer Use Agents

arXiv:2609.24890v1 Announce Type: cross Abstract: Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with f...

By Zhilin Wang, Shaokun Zhang, Yifan Zhang, Hao Zhang, Jin Xu, Binfeng Xu, Jian Hu, Yunheng Zou, Karan Sapra, Andrew Tao, Jan Kautz, Yi Dong

llms agents benchmarks

arXiv AI

Aug 18

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

arXiv:2608. 16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages.

By Zhenhang Nie (iFLYTEK Co., Ltd., Hefei, China), Gui Zheng (iFLYTEK Co., Ltd., Hefei, China), Xudong Sun (iFLYTEK Co., Ltd., Hefei, China), Tailong Zhu (iFLYTEK Co., Ltd., Hefei, China), Bin Zhang (iFLYTEK Co., Ltd., Hefei, China)

agents benchmarks

arXiv AI

Jun 11

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

arXiv:2606. 11520v1 Announce Type: cross Abstract: Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution--properties absent from existing datasets.

By Siyuan Luo, Nairong Zheng, Lin Zhou, Tiankuo Yao, Shengyou Yuan, Haojia Yu, Cong Pang, Jiapeng Luo, Lewei Lu

llms rag agents fine-tuning benchmarks

arXiv AI

Jul 29

Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?

arXiv:2607. 26041v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks.

By Abhishek Pillai, Samir Kumar Nayak, Yuan Chen

agents benchmarks

arXiv AI

Jul 15

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

arXiv:2606. 29537v2 Announce Type: replace Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.

By Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, Weiming Wu, Jiayang Sun, Jiamin Song, Kaiqian Cui, Bowen Wang, Haoyuan Wu, Yitong Li, Dunjie Lu, Haikong Lu, Qi Zhen, Xinyuan Wang, Jiaqi Deng, Yuhao Yang, Cheng Chen, Boyuan Zheng, Alex Su, Xiao Yu, Hao Zou, Saaket Agashe, Xing Han Lu, Manpreet Kaur, Zhengyang Qi, Vincent Sunn Chen, Frederic Sala, Dayiheng Liu, Junyang Lin, Zhou Yu, Yu Su, Siva Reddy, Xin Eric Wang, Peng Qi, Tianbao Xie, Tao Yu

llms agents benchmarks safety

arXiv AI

Jun 30

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

arXiv:2606. 29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.

llms agents benchmarks safety

arXiv AI

Jun 8

MacArena: Benchmarking Computer Use Agents on an Online macOS Environment

arXiv:2606. 06560v1 Announce Type: cross Abstract: Computer-use agents (CUAs) operate graphical user interfaces (GUIs) through vision and control primitives, and their capabilities have advanced rapidly, driven in part by standardized online evaluation benchmarks such as OSWorld, which serve both as evaluation tools and as training environments for reinforcement learning.

By Victor Muryn, Maksym Shamrai, Sofiia Mazepa, Yehor Khodysko

agents reinforcement-learning benchmarks

arXiv AI

Sep 4

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Terminal-Universe is a framework that transforms large collections of terminal‑based agent trajectories into reusable, executable environments. By replaying recorded file operations and completing missing files, it reconstructs the original workspace and task, then synthesizes new tasks and multi‑round interactions. The resulting 37.3k task‑sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑based benchmarks.

By Jie Wu, Zhenru Zhang, Beichen Zhang, Xuwu Wang, Yuhui Su, Mouxiang Chen, Peng Wang, Zhihai Wang, Que Shen, Hao Zhou, An Yang, Fei Huang, Yujiu Yang, Dayiheng Liu

agents fine-tuning

Related stories