7 papers
SkillShield: Prompt-Space Security Skills for LLM Coding Agents
Xiaodong Wu, Zhimin Zhao, Qi Li +4
A coding agent edits files and executes shell commands with its developer's privileges, allowing malicious requests to translate directly into harmful actions or functional malware…
EVOMAL: Self-Poisoning in Self-Evolving Coding Agents
Xiaodong Wu, Yu Shi, Qi Li +5
Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retri…
Gradual Cognitive Externalization: From Modeling Cognition to Constituting It
Zhimin Zhao
Developers are publishing AI agent skills that replicate a colleague's communication style, encode a supervisor's mentoring heuristics, or preserve a person's behavioral repertoire…
Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning
Zhimin Zhao
This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the…
SWE-Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering
Zhimin Zhao
Foundation models (FMs), particularly large language models (LLMs), have shown significant promise in various software engineering (SE) tasks, including code generation, debugging,…
On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards
Zhimin Zhao, Abdul Ali Bangash, Filipe Roseiro Côgo +2
Foundation models (FM), such as large language models (LLMs), which are large-scale machine learning (ML) models, have demonstrated remarkable adaptability in various downstream so…