ExeRScope uses static and dynamic program analysis to show that LLMs' code execution reasoning degrades with program complexity, nested structures, longer loops, and non-primitive types.
Python AST module
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models
ExeRScope uses static and dynamic program analysis to show that LLMs' code execution reasoning degrades with program complexity, nested structures, longer loops, and non-primitive types.