activity
20242026
collaborators

7 papers

cs.CR2026

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…

cs.CR2026

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…

cs.AI2026

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…

cs.LG2026

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…

cs.SE2025

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,…

cs.SE2024

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…