Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Changshu, Ghazanfari, Alireza, Chen, Yang, Jabbarvand, Reyhaneh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917431547527168
author Liu, Changshu
Ghazanfari, Alireza
Chen, Yang
Jabbarvand, Reyhaneh
author_facet Liu, Changshu
Ghazanfari, Alireza
Chen, Yang
Jabbarvand, Reyhaneh
contents Code reasoning tasks are becoming prevalent in large language model (LLM) assessments. Yet, there is a dearth of studies on the impact of real-world complexities on code reasoning, e.g., inter- or intra-procedural dependencies, API calls, deeply nested constructs, and non-primitive complex types. Evaluating LLMs under such a simplistic setting poses a significant threat to assumptions about their generalizability in practice. To enable a more realistic evaluation of code reasoning, we construct a dataset of 1200 reasoning problems from two sources: existing code reasoning benchmarks and popular GitHub Python repositories. Our pipeline leverages static and dynamic program analysis to automatically serialize/deserialize compound, complex, and custom types galore in real-world code, going far beyond only primitive types used in prior studies. A key feature of our dataset is categorizing each reasoning problem as Lower Complexity (LC) or Higher Complexity (HC) via a principled majority-vote mechanism over nine diverse and interpretable code-complexity metrics, yielding two well-separated, semantically meaningful categories of problem difficulty suitable for precise calibration of LLM reasoning ability. This categorization shows that the problems used in existing code-reasoning evaluation mostly belong to the LC category, failing to represent real-world complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14917
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings
Liu, Changshu
Ghazanfari, Alireza
Chen, Yang
Jabbarvand, Reyhaneh
Software Engineering
Code reasoning tasks are becoming prevalent in large language model (LLM) assessments. Yet, there is a dearth of studies on the impact of real-world complexities on code reasoning, e.g., inter- or intra-procedural dependencies, API calls, deeply nested constructs, and non-primitive complex types. Evaluating LLMs under such a simplistic setting poses a significant threat to assumptions about their generalizability in practice. To enable a more realistic evaluation of code reasoning, we construct a dataset of 1200 reasoning problems from two sources: existing code reasoning benchmarks and popular GitHub Python repositories. Our pipeline leverages static and dynamic program analysis to automatically serialize/deserialize compound, complex, and custom types galore in real-world code, going far beyond only primitive types used in prior studies. A key feature of our dataset is categorizing each reasoning problem as Lower Complexity (LC) or Higher Complexity (HC) via a principled majority-vote mechanism over nine diverse and interpretable code-complexity metrics, yielding two well-separated, semantically meaningful categories of problem difficulty suitable for precise calibration of LLM reasoning ability. This categorization shows that the problems used in existing code-reasoning evaluation mostly belong to the LC category, failing to represent real-world complexity.
title Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings
topic Software Engineering
url https://arxiv.org/abs/2512.14917