8 papers
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
Ningzhi Tang, Chaoran Chen, Gelei Xu +5
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually ex…
An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
Gelei Xu, Ningzhi Tang, Xueyang Li +4
Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Agent skills, self-contained di…
NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation
Ningzhi Tang, David Meininger, Gelei Xu +4
Code modification requires developers to comprehend code, plan changes, articulate intent, and validate outcomes, making it cognitively demanding. While natural language (NL) code…
Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions
Ningzhi Tang, Chaoran Chen, Zihan Fang +6
IDE-integrated AI coding assistants, which operate conversationally within developers' working codebases with access to project context and multi-file editing, are rapidly reshapin…
Patient-Conditioned Adaptive Offsets for Reliable Diagnosis across Subgroups
Gelei Xu, Yuying Duan, Jun Xia +3
AI models for medical diagnosis often exhibit uneven performance across patient populations due to heterogeneity in disease prevalence, imaging appearance, and clinical risk profil…
AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays
Xueyang Li, Mingze Jiang, Gelei Xu +4
Agentic AI is advancing rapidly, yet truly autonomous medical-imaging triage, where a system decides when to stop, escalate, or defer under real constraints, remains relatively und…