English
Related papers

Related papers: Synthesizing Performance Constraints for Evaluatin…

200 papers

In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight…

Software Engineering · Computer Science 2024-10-29 William Murphy , Nikolaus Holzer , Feitong Qiao , Leyi Cui , Raven Rothkopf , Nathan Koenig , Mark Santolucito

Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should…

Software Engineering · Computer Science 2024-10-31 Minju Seo , Jinheon Baek , Sung Ju Hwang

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure…

Cryptography and Security · Computer Science 2026-05-12 Houjun Liu , Lisa Einstein , John Yang , Joachim Baumann , Duncan Eddy , Christopher D. Manning , Mykel Kochenderfer , Diyi Yang

Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their…

Software Engineering · Computer Science 2025-07-17 Xinyi He , Qian Liu , Mingzhe Du , Lin Yan , Zhijie Fan , Yiming Huang , Zejian Yuan , Zejun Ma

Large language models (LLMs) have demonstrated impressive capabilities in code generation, where the natural language prompt plays a crucial role in conveying user intent to the model. However, prior studies have shown that LLMs are highly…

Software Engineering · Computer Science 2025-12-11 Shuhan Liu , Xing Hu , Kerui Huang , Xiaohu Yang , David Lo , Xin Xia

While recent advances in large language models (LLMs) have shown promise in automating test generation for regression testing, they often suffer from limited reasoning about program execution, resulting in stagnated coverage growth - a…

Software Engineering · Computer Science 2026-01-28 Cuong Chi Le , Cuong Duc Van , Tung Duy Vu , Thai Minh Pham Vu , Hoang Nhat Phan , Huy Nhat Phan , Tien N. Nguyen

Configuration settings are essential for tailoring software behavior to meet specific performance requirements. However, incorrect configurations are widespread, and identifying those that impact system performance is challenging due to the…

Software Engineering · Computer Science 2024-06-19 Zehao Wang , Dong Jae Kim , Tse-Hsun Chen

Large language models for code generation increasingly rely on synthetic data, where both problem solutions and verification tests are generated by models. While this enables scalable data creation, it introduces a previously unexplored…

Software Engineering · Computer Science 2025-09-26 Srishti Gureja , Elena Tommasone , Jingyi He , Sara Hooker , Matthias Gallé , Marzieh Fadaee

We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding benchmarks often fail to provide reliable insights into code…

Software Engineering · Computer Science 2024-08-14 Jiawei Liu , Songrun Xie , Junhao Wang , Yuxiang Wei , Yifeng Ding , Lingming Zhang

Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. However, the increasing size and complexity of LLMs present…

Machine Learning · Computer Science 2024-06-18 Yingbing Huang , Lily Jiaxin Wan , Hanchen Ye , Manvi Jha , Jinghua Wang , Yuhong Li , Xiaofan Zhang , Deming Chen

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this…

Software Engineering · Computer Science 2025-08-29 Yunlong Feng , Yang Xu , Xiao Xu , Binyuan Hui , Junyang Lin

While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse programming tasks. Dynamically selecting the optimal LLM…

Software Engineering · Computer Science 2025-06-13 Junhang Cheng , Fang Liu , Chengru Wu , Li Zhang

Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through…

Software Engineering · Computer Science 2025-11-19 Florentina Voboril , Vaidyanathan Peruvemba Ramaswamy , Stefan Szeider

Evaluating Large Language Models (LLMs) with respect to real-world code complexity is essential. Otherwise, there is a risk of overestimating LLMs' programming abilities based on simplistic benchmarks, only to be disappointed when using…

Software Engineering · Computer Science 2026-02-24 Yang Chen , Shuyang Liu , Reyhaneh Jabbarvand

Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually designing and maintaining rules for specific performance bugs (e.g., redundant…

Software Engineering · Computer Science 2025-12-30 Yue Wu , Minghao Han , Ruiyin Li , Peng Liang , Amjed Tahir , Zengyang Li , Qiong Feng , Mojtaba Shahin

Large Language models (LLMs) have demonstrated significant potential in text-to-SQL reasoning tasks, yet a substantial performance gap persists between existing open-source models and their closed-source counterparts. In this paper, we…

Computation and Language · Computer Science 2025-09-23 Yu Guo , Dong Jin , Shenghao Ye , Shuangwu Chen , Jian Yang , Xiaobin Tan

The weakest precondition (WP) of a program describes the largest set of initial states from which all terminating executions of the program satisfy a given postcondition. The generation of WPs is an important task with practical…

Software Engineering · Computer Science 2025-12-18 Daragh King , Vasileios Koutavas , Laura Kovacs

Large Language Models (LLMs) have demonstrated significant capability in code generation, but their potential in code efficiency optimization remains underexplored. Previous LLM-based code efficiency optimization approaches exclusively…

Software Engineering · Computer Science 2025-10-22 Xiaoxue Ren , Jun Wan , Yun Peng , Zhongxin Liu , Ming Liang , Dajun Chen , Wei Jiang , Yong Li

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…

Software Engineering · Computer Science 2024-07-09 Yun-Da Tsai , Mingjie Liu , Haoxing Ren

Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified synthesis requires consistent artifacts across several coupled…

Machine Learning · Computer Science 2026-05-15 Robert Joseph George , Carson Eisenach , Udaya Ghai , Dominique Perrault-Joncas , Anima Anandkumar , Dean Foster