As agents perform tasks autonomously in local and cloud environments, auditing their execution trajectories can help service providers identify risks and improve agent harnesses and foundation models. Our analysis of production and red-team trajectories shows that some risks are repeatedly missed across auditing config...
Zi-Peng Ye, Shen-Yu Dai, Yong Xie et al.· 0 citations
A preliminary study shows that verification has the strongest association with task success, but often occurs late, leaving limited opportunities for correction, and that the proportion of duty-relevant information decreases as records from different duties accumulate in a shared context.
Xue-Xin Shen, Lingyong Yan, Shuai-Qiang Wang et al.· 0 citations
Recommendation systems have become crucial tools for mitigating information overload and enhancing user experience. Among them, LightGCN has achieved remarkable results in both efficiency and performance by simplifying graph convolution operations. However, in scenarios with sparse training data, LightGCN tends to prod...
This work introduces a temporal-graph-learning (TGL) controller that learns these predictions jointly and supplies both outputs in one forward pass, and shows that a small graph model can handle both decisions and improve the language agents it controls.
Xiaoze Liu, Ruowang Zhang, Amir H. Abdi et al.· 2 citations
Through this design, CDNE incorporates local node proximity and mesoscopic community semantics without relying on an open-ended iterative procedure, and achieves strong performance in link prediction, cross-layer network reconstruction, and community-quality evaluation.
Zhikai Chen, He-Gui Zhang, Yang Wu et al.· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.