English
Related papers

Related papers: SlopCodeBench: Benchmarking How Coding Agents Degr…

200 papers

Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase.…

Software Engineering · Computer Science 2026-02-11 Muxin Tian , Zhe Wang , Blair Yang , Zhenwei Tang , Kunlun Zhu , Honghua Dong , Hanchen Li , Xinni Xie , Guangjing Wang , Jiaxuan You

Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this…

Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue. Neither isolates the distinct skill of property-based testing: deriving a…

Software Engineering · Computer Science 2026-05-21 Lucas Jing , Xinqi Wang , Liao Zhang , Simon S. Du

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…

As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…

Artificial Intelligence · Computer Science 2026-04-02 Chris Ge , Daria Kryvosheieva , Daniel Fried , Uzay Girit , Kaivalya Hariharan

As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full…

Software Engineering · Computer Science 2026-05-08 Ye Shang , Quanjun Zhang , Haichuan Hu , Chunrong Fang , Liang Xiao , Zhenyu Chen

While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal…

Machine Learning · Computer Science 2026-03-17 Yi-Xuan Deng , Xiaoqin Liu , Yi Zhang , Guo-Wei Yang , Shuojin Yang

Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing benchmarks often focus on algorithmic…

We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…

Software Engineering · Computer Science 2026-03-30 Deepak Kumar

As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical. While existing benchmarks like…

While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce…

Artificial Intelligence · Computer Science 2026-03-17 Shengda Fan , Xuyan Ye , Yupeng Huo , Zhi-Yuan Chen , Yiju Guo , Shenzhi Yang , Wenkai Yang , Shuqi Ye , Jingwen Chen , Haotian Chen , Xin Cong , Yankai Lin

Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-flag performance. Classical binary reverse engineering remains less precisely specified:…

Software Engineering · Computer Science 2026-05-12 Isaac David , Arthur Gervais

AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If models could reliably write such code, the research of our…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Wenyi Li , Renkai Luo , Yue Yu , Huan-ang Gao , Mingju Gao , Li Yuan , Chaoyou Fu , Hao Zhao

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…

Software Engineering · Computer Science 2026-05-29 Ningzhi Tang , Chaoran Chen , Gelei Xu , Yiyu Shi , Yu Huang , Collin McMillan , Tao Dong , Toby Jia-Jun Li

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…

Artificial Intelligence · Computer Science 2026-05-21 Zhengkang Guo , Yiyang Li , Lin Qiu , Xiaohua Wang , Jingwen Xv , Dongyu Ru , Xiaoyu Li , Xiaoqing Zheng , Xuezhi Cao , Xunliang Cai

Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation,…

Cryptography and Security · Computer Science 2026-05-06 Jonathan Steinberg , Oren Gal

Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on end-to-end tasks such as issue resolution truly reflects repository context reasoning, the…

Software Engineering · Computer Science 2026-05-27 Hanyu Li , Yichi Zhang , Speed Zhu , Hang Su , Jun Zhu , Yinpeng Dong

Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing. However, in the real world, the development of mature software is typically predicated on…

Software Engineering · Computer Science 2026-04-02 Jialong Chen , Xander Xu , Hu Wei , Chuan Chen , Bing Zhao

As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…

Computation and Language · Computer Science 2025-12-02 Hyunjun Kim , Sooyoung Ryu