English
Related papers

Related papers: Exploring the Potential of Conversational Test Sui…

200 papers

Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible…

Computation and Language · Computer Science 2024-10-11 Samuel Arcadinho , David Aparicio , Mariana Almeida

While there has been plenty of work on generating tests from existing code, there has been limited work on generating tests from issues. A correct test must validate the code patch that resolves the issue. This paper focuses on the scenario…

Software Engineering · Computer Science 2025-06-02 Toufique Ahmed , Jatin Ganhotra , Rangeet Pan , Avraham Shinnar , Saurabh Sinha , Martin Hirzel

The development of natural language processing algorithms and the explosive growth of conversational data are encouraging researches on the human-computer conversation. Still, getting qualified conversational data on a large scale is…

Computation and Language · Computer Science 2020-02-13 Sihyeon Jo , Seungryong Yoo , Sangwon Im , Seung Hee Yang , Tong Zuo , Hee-Eun Kim , SangWook Han , Seong-Woo Kim

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic…

Machine Learning · Computer Science 2025-10-23 Hwiwon Lee , Ziqi Zhang , Hanxiao Lu , Lingming Zhang

Failure-inducing inputs play a crucial role in diagnosing and analyzing software bugs. Bug reports typically contain these inputs, which developers extract to facilitate debugging. Since bug reports are written in natural language, prior…

Software Engineering · Computer Science 2025-12-16 Alif Al Hasan , Subarna Saha , Mia Mohammad Imran , Tarannum Shaila Zaman

Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free…

Personalized review generation helps businesses understand user preferences, yet most existing approaches assume extensive review histories of the target user or require additional model training. Real-world applications often face few-shot…

Computation and Language · Computer Science 2025-09-26 Genki Kusano

In conversation, speakers produce language incrementally, word by word, while continuously monitoring the appropriateness of their own contribution in the dynamically unfolding context of the conversation; and this often leads them to…

Computation and Language · Computer Science 2023-08-24 Arash Eshghi , Arash Ashrafzadeh

Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub…

Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention. However, existing tools tend to generate patches that satisfy test cases without fixing the underlying bug, those are known as…

Software Engineering · Computer Science 2025-07-31 Marcos Fuster-Pena , David de-Fitero-Dominguez , Antonio Garcia-Cabot , Eva Garcia-Lopez

Automatic program repair (APR) aims to reduce the manual efforts required to identify and fix errors in source code. Before the rise of LLM-based agents, a common strategy was to increase the number of generated patches, sometimes to the…

Software Engineering · Computer Science 2025-05-07 Fernando Vallecillos Ruiz , Max Hort , Leon Moonen

Recent work in automated program repair (APR) proposes the use of reasoning and patch validation feedback to reduce the semantic gap between the LLMs and the code under analysis. The idea has been shown to perform well for general APR, but…

Software Engineering · Computer Science 2024-05-27 Ummay Kulsum , Haotian Zhu , Bowen Xu , Marcelo d'Amorim

Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…

Computation and Language · Computer Science 2022-11-02 Sean Welleck , Ximing Lu , Peter West , Faeze Brahman , Tianxiao Shen , Daniel Khashabi , Yejin Choi

Despite the immense popularity of the Automated Program Repair (APR) field, the question of patch validation is still open. Most of the present-day approaches follow the so-called Generate-and-Validate approach, where first a candidate…

Software Engineering · Computer Science 2021-04-01 Viktor Csuvik , Dániel Horváth , Márk Lajkó , László Vidács

We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g.,…

Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with…

Software Engineering · Computer Science 2026-04-08 Kai Yu , Zhenhao Zhou , Junhao Zeng , Ying Wang , Xueying Du , Zhiqiang Yuan , Junwei Liu , Ziyu Zhou , Yujia Wang , Chong Wang , Xin Peng

Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…

Computation and Language · Computer Science 2023-05-16 Sean Paulsen

Automated generation of feedback on programming assignments holds significant benefits for programming education, especially when it comes to advanced assignments. Automated Program Repair techniques, especially Large Language Model based…

Software Engineering · Computer Science 2024-04-03 Qianhui Zhao , Fang Liu , Li Zhang , Yang Liu , Zhen Yan , Zhenghao Chen , Yufei Zhou , Jing Jiang , Ge Li

Automatic program repair holds the potential of dramatically improving the productivity of programmers during the software development process and correctness of software in general. Recent advances in machine learning, deep learning, and…

Software Engineering · Computer Science 2021-09-24 Hossein Hajipour , Apratim Bhattacharyya , Cristian-Alexandru Staicu , Mario Fritz

SPEculative Execution side Channel Hardware (SPEECH) Vulnerabilities have enabled the notorious Meltdown, Spectre, and L1 terminal fault (L1TF) attacks. While a number of studies have reported different variants of SPEECH vulnerabilities,…

Cryptography and Security · Computer Science 2019-12-11 Yuan Xiao , Yinqian Zhang , Radu Teodorescu