20 citations · 67 across the 35 of their papers we have counts for
14 papers · 1 filter
On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces
Ahmed Hereiz, Yingzhe Lyu, Hao Li +2
AI coding agents, software tools that automate development tasks through reasoning and tool use, are increasingly extended through plugin marketplaces, yet the structure, maintenan…
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…
Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents
Zehao Wang, Yisen Xu, Chenglin Li +5
Long-horizon coding agents accumulate hundreds of actions and observations in their trajectories, yet nothing in this record indicates which observations still describe the reposit…
When Model Release Meets Model Reuse: Producer-Consumer Misalignment in Hugging Face
Adekunle Ajibode, Oussama Ben Sghaier, Bram Adams +1
Pre-trained Language Models (PTLMs) are increasingly reused as dependencies in modern software systems, even though prior work has documented persistent structural problems in PTLM…
Don't Trust the Label: License Laundering in AI Supply Chains
James Jewitt, Hao Li, Gopi Krishnan Rajbahadur +2
AI artifacts move through a multi-platform supply chain, spanning datasets and models on Hugging Face and applications on GitHub. While each artifact carries a license whose obliga…
Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality
Oussama Ben Sghaier, Hao Li, Bram Adams +1
Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agent harness: a middleware layer in between a developer and…
Towards Imputation of Pre-Trained Language Model Metadata using Semantic Fingerprinting
Adekunle Ajibode, Oussama Ben Sghaier, Keheliya Gallaba +2
Pre-trained language models (PTLMs) hosted on platforms such as Hugging Face form complex lineage structures similar to software dependency graphs. However, unlike traditional soft…
Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild
Zhimin Zhao, Zehao Wang, Abdul Ali Bangash +2
Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their crit…
From Leaderboard to Deployment: Code Quality Challenges in AV Perception Repositories
Mateus Karvat, Bram Adams, Sidney Givigi
Autonomous vehicle (AV) perception models are typically evaluated solely on benchmark performance metrics, with limited attention to code quality, production readiness and long-ter…
Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity
James Jewitt, Gopi Krishnan Rajbahadur, Hao Li +2
Permissive licenses like MIT, Apache-2.0, and BSD-3-Clause dominate open-source AI, signaling that artifacts like models, datasets, and code can be freely used, modified, and redis…
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions
Mohammed Mehedi Hasan, Hao Li, Gopi Krishnan Rajbahadur +2
The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. Ho…
AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit Identification
Yu Shi, Hao Li, Bram Adams +1
Identifying Bug-Inducing Commits (BICs) is fundamental for understanding software defects and enabling downstream tasks such as defect prediction and automated program repair. Yet…
Assessing and Improving the Representativeness of Code Generation Benchmarks Using Knowledge Units (KUs) of Programming Languages -- An Empirical Study
Md Ahasanuzzaman, Bram Adams, Emad Fallahzadeh +2
Large Language Models (LLMs) such as GPT-4, Claude and LLaMA have shown impressive performance in code generation, typically evaluated using benchmarks (e.g., HumanEval). However,…