From the 1 of 9 linked papers with an AI index.
9 papers
When is LLM-Based Program Reasoning Correct? A Completion Semantics for LLM-Based Code Inference
Zhiyuan Liu, Yihe Li, Trevor E. Carlson +3
The paper defines a completion semantics for reasoning about incomplete code fragments generated by large language models, and introduces a witness-generation workflow to validate…
Reachability Across the NL/PL Boundary: A Taxonomy-Driven Dataflow Model for LLM-Integrated Applications
Zihao Xu, Xiao Cheng, Ruijie Meng +1
LLM API calls have become a standard programming primitive, but they create a program boundary that disrupts traditional dataflow analysis. A runtime value may be inserted into a n…
Understanding the (In)Security of Vibe-Coded Applications
Junquan Deng, Zhiyu Fan, Ruijie Meng
Recent advances in large language models (LLMs) have enabled vibe coding, an emerging software development paradigm in which users create applications primarily through natural-lan…
Large Language Model assisted Hybrid Fuzzing
Ruijie Meng, Gregory J. Duck, Abhik Roychoudhury
Greybox fuzzing is one of the most popular methods for detecting software vulnerabilities, which conducts a biased random search within the program input space. To enhance its effe…
Agentic Verification of Software Systems
Haoxin Tu, Huan Zhao, Yahui Song +3
Automatically generated code is gaining traction recently, owing to the prevalence of Large Language Models (LLMs). Further, the AlphaProof initiative has demonstrated the possibil…
VeriGrey: Greybox Agent Validation
Yuntong Zhang, Sungmin Kang, Ruijie Meng +2
Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decis…