From the 1 of 6 linked papers with an AI index.
6 papers
SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements
Pengyu Xue, He Yang Yuan, Xin Wang +6
The paper introduces SWE-NFI, a benchmark that assesses how coding agents can make non-functional, behavior-preserving improvements to Python code, using real pull‑request tasks an…
A Multi-Language Perspective on the Robustness of LLM Code Generation
Fazle Rabbi, Zishuo Ding, Jinqiu Yang
Large language models have gained significant traction and popularity in recent times, extending their usage to code-generation tasks. While this field has garnered considerable at…
A Mathematics-Guided Approach to Floating-Point Error Detection
Youshuai Tan, Zhanwei Zhang, Zishuo Ding +3
Floating-point program errors can lead to severe consequences, particularly in critical domains such as military applications. Only a small subset of inputs may induce substantial…
OFP-Repair: Repairing Floating-point Errors via Original-Precision Arithmetic
Youshuai Tan, Zishuo Ding, Jinfu Chen +1
Errors in floating-point programs can lead to severe consequences, particularly in critical domains such as military, aerospace, and financial systems, making their repair a crucia…
Computing Floating-Point Errors by Injecting Perturbations
Youshuai Tan, Zhanwei Zhang, Jinfu Chen +3
Floating-point programs form the foundation of modern science and engineering, providing the essential computational framework for a wide range of applications, such as safety-crit…
DELA: A Novel Approach for Detecting Errors Induced by Large Atomic Condition Numbers
Youshuai Tan, Zhanwei Zhang, Jinfu Chen +3
Numerical programs form the foundation of modern science and engineering, providing essential solutions to complex mathematical problems. Therefore, errors in numerical results wou…