3 papers
cs.SE2026
ConceptCoder: Improve Code Reasoning via Concept Learning
Md Mahbubur Rahman, Hengbo Tong, Wei Le
Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD).…
cs.SE2026
CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
Monoshi Kumar Roy, Simin Chen, Benjamin Steenhoek +4
Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasonin…
cs.SE2025
To Err is Machine: Vulnerability Detection Challenges LLM Reasoning
Benjamin Steenhoek, Md Mahbubur Rahman, Monoshi Kumar Roy +5
In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoni…