English
Related papers

Related papers: SWE-Mirror: Scaling Issue-Resolving Datasets by Mi…

200 papers

Scaling laws predict that the performance of large language models improves with increasing model size and data size. In practice, pre-training has been relying on massive web crawls, using almost all data sources publicly available on the…

Computation and Language · Computer Science 2025-09-16 Thao Nguyen , Yang Li , Olga Golovneva , Luke Zettlemoyer , Sewoong Oh , Ludwig Schmidt , Xian Li

The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require fewer samples but have been researched less. As…

A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically.…

Software Engineering · Computer Science 2026-01-26 Toufique Ahmed , Jatin Ganhotra , Avraham Shinnar , Martin Hirzel

The rapid progress in Automated Program Repair (APR) has been driven by advances in AI, particularly large language models (LLMs) and agent-based systems. SWE-Bench is a recent benchmark designed to evaluate LLM-based repair systems using…

Software Engineering · Computer Science 2026-02-06 Matias Martinez , Xavier Franch

Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across diverse environments. However, existing RL benchmarks lack the…

Test-time scaling via solution sampling and aggregation has become a key paradigm for improving the reasoning performance of Large Language Models (LLMs). While reward model selection is commonly employed in this approach, it often fails to…

Machine Learning · Computer Science 2025-09-30 Zhicheng Yang , Zhijiang Guo , Yinya Huang , Yongxin Wang , Yiwei Wang , Xiaodan Liang , Jing Tang

Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data. While the open development of large high-quality English pre-training datasets has seen substantial recent progress, training…

GitHub's issue reports provide developers with valuable information that is essential to the evolution of a software development project. Contributors can use these reports to perform software engineering tasks like submitting bugs,…

Software Engineering · Computer Science 2023-03-22 Nafiseh Nikeghbal , Amir Hossein Kargaran , Abbas Heydarnoori , Hinrich Schütze

Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS)…

Software Engineering · Computer Science 2025-05-29 Tobias Lindenbauer , Egor Bogomolov , Yaroslav Zharov

Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thought (CoT) data. To address this, we propose the GeoSym Engine, an automated and scalable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jinhao Jing , Zheng Ma , Jinwei Liang , Qiannian Zhao , Shawn Chen , Jing Yang , Por Lip Yee , Prayag Tiwari , Jingjing Bai , Benyou Wang , Lewei Lu , Zhan Su

Resolving real-world software engineering (SWE) issues with autonomous agents requires complex, long-horizon reasoning. Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally…

Software Engineering · Computer Science 2026-04-17 Hao Han , Jin Xie , Xuehao Ma , Weiquan Zhu , Ziyao Zhang , ZhiLiang Long , Hongkai Chen , Qingwen Ye

Large language models (LLMs) have exhibited great potential in mathematical reasoning. However, there remains a performance gap in this area between existing open-source models and closed-source models such as GPT-4. In this paper, we…

Computation and Language · Computer Science 2024-09-12 Zimu Lu , Aojun Zhou , Houxing Ren , Ke Wang , Weikang Shi , Junting Pan , Mingjie Zhan , Hongsheng Li

We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focused coding benchmarks and self-contained training testbeds.…

Machine Learning · Computer Science 2025-04-22 Yunhui Xia , Wei Shen , Yan Wang , Jason Klein Liu , Huifeng Sun , Siyue Wu , Jian Hu , Xiaolong Xu

Recent advancements in large language models (LLMs) suggest great promises in code and proof generations. However, scaling automated formal verification to real-world projects requires resolving cross-module dependencies and global…

Software Engineering · Computer Science 2025-10-01 Si Cheng Zhong , Xujie Si

Issue resolution has made remarkable progress thanks to the advanced reasoning capabilities of large language models (LLMs). Recently, agent-based frameworks such as SWE-agent have further advanced this progress by enabling autonomous,…

Software Engineering · Computer Science 2025-08-01 Han Li , Yuling Shi , Shaoxin Lin , Xiaodong Gu , Heng Lian , Xin Wang , Yantao Jia , Tao Huang , Qianxiang Wang

Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from the repository, they…

Software Engineering · Computer Science 2026-02-10 Boshi Wang , Weijian Xu , Yunsheng Li , Mei Gao , Yujia Xie , Huan Sun , Dongdong Chen

Recent advances in LLM-based decompilers have been shown effective to convert low-level binaries into human-readable source code. However, there still lacks a comprehensive benchmark that provides large-scale binary-source function pairs,…

Software Engineering · Computer Science 2025-10-21 Hanzhuo Tan , Xiaolong Tian , Hanrui Qi , Jiaming Liu , Zuchen Gao , Siyi Wang , Qi Luo , Jing Li , Yuqun Zhang

Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing…

Software Engineering · Computer Science 2025-11-21 KeFan Li , Mengfei Wang , Hengzhi Zhang , Zhichao Li , Yuan Yuan , Mu Li , Xiang Gao , Hailong Sun , Chunming Hu , Weifeng Lv

Replication packages are crucial for enabling transparency, validation, and reuse in software engineering (SE) research. While artifact sharing is now a standard practice and even expected at premier SE venues such as ICSE, the practical…

Software Engineering · Computer Science 2026-03-24 Al Muttakin , Saikat Mondal , Chanchal K. Roy

Large Language Models have achieved strong performance on reasoning tasks, solving competition-level coding and math problems. However, their scalability is limited by human-labeled datasets and the lack of large-scale, challenging coding…

Computation and Language · Computer Science 2025-10-21 Hanxu Hu , Xingxing Zhang , Jannis Vamvas , Rico Sennrich , Furu Wei