5 papers
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents
Hang Yan, Xinyu Che, Fangzhi Xu +7
Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time I…
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent
Bowen Yang, Kaiming Jin, Zhenyu Wu +12
While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalizati…
OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models
Zhenyu Wu, Jingjing Xie, Zehao Li +8
With VLM-powered computer-using agents (CUAs) becoming increasingly capable at graphical user interface (GUI) navigation and manipulation, reliable step-level decision-making has e…
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
Fangzhi Xu, Hang Yan, Chang Ma +6
Advancing LLM reasoning skills has captivated wide interest. However, current post-training techniques rely heavily on supervisory signals, such as outcome supervision or auxiliary…
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
Kanzhi Cheng, Wenpo Song, Jiaxin Fan +7
Image captioning has been a longstanding challenge in vision-language research. With the rise of LLMs, modern Vision-Language Models (VLMs) generate detailed and comprehensive imag…