3 papers
cs.SE2026
Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study
Yuchen Shao, Wenjing Liu, Yuheng Huang +6
Large language model (LLM) agents increasingly complete tasks through live graphical user interfaces (GUIs). Because the model cannot directly operate the GUI, these systems often…
cs.AI2026
FedSkillGit: Federated Skill Evolution via Version Control
Boxun Lan, Jiamei Li, Weijian Li +5
Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deployments, this experience is dis…
cs.LG2026
Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
Ziqun Bao, Xinyu Zhang, Yuchen Shao +1
Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of available evaluations. This wor…