From the 1 of 5 linked papers with an AI index.
5 papers
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong +33
The paper presents OSWorld 2.0, a benchmark consisting of 108 long‑horizon, real‑world computer‑use workflows designed to evaluate how well AI agents can handle complex, multi‑step…
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
Tianbao Xie, Jiaqi Deng, Xiaochuan Li +12
Graphical user interface (GUI) grounding, the ability to map natural language instructions to specific actions on graphical user interfaces, remains a critical bottleneck in comput…
VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos
Dunjie Lu, Yiheng Xu, Junli Wang +12
Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgen…
EVOR: Evolving Retrieval for Code Generation
Hongjin Su, Shuyang Jiang, Yuhang Lai +5
Recently the retrieval-augmented generation (RAG) has been successfully applied in code generation. However, existing pipelines for retrieval-augmented code generation (RACG) emplo…
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Ruisheng Cao, Fangyu Lei, Haoyuan Wu +20
Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs)…