SWE‑Gate is a new repository‑level benchmark that evaluates software engineering agents on both functional correctness and review‑derived acceptance constraints. It creates 303 repair instances from real pull‑request review comments across 75 open‑source Python projects, providing separate functional and constraint tests along with compliant and non‑compliant patches. Experiments with four LLM backends show that while 644 repairs pass functional tests, 221 fail to meet the review constraints, highlighting a gap between functional success and full repair compliance.
By Xin He, Yanlin Wang, Mingwei Liu, Jiachi Chen, Hongyu Zhang, Guanbin Li
arXiv:2607. 03316v1 Announce Type: cross Abstract: Agentic code review, where autonomous agents provide code review comments on pull requests, is increasingly integrated into development workflows, yet there is limited empirical evidence on how developers respond to such comments in practice.
By Hong Yi Lin, Mingzhao Liang, Kla Tantithamthavorn, Patanamon Thongtanunam
arXiv:2607. 08981v1 Announce Type: cross Abstract: LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed.
By Viraaji Mothukuri, Reza M. Parizi
The paper presents a systematic analysis of five state‑of‑the‑art automated program repair agents, tracing their decision‑making across 500 real‑world repair tasks. It finds that while the agents perform well on simple fixes, they struggle with logic‑intensive bugs, often producing verbose, overfitted patches that pass tests without addressing root causes. Key bottlenecks identified include poor test generation, limited regression test selection, and reliance on primitive tooling without access to debuggers or advanced program analysis tools.
By Ira Ceka, Hailie Mitchell, Saurabh Pujar, Luca Buratti, Shyam Ramji, Junfeng Yang, Gail Kaiser, Baishakhi Ray
The paper introduces MCR-Bench, a benchmark for realistic multi‑round code review that includes 2,269 real‑world tasks across five programming languages, each annotated with fine‑grained defect information and dynamic state labels. Experiments with mainstream large language models show limited overall performance, especially as interaction rounds increase, and reveal that model accuracy varies by defect type and severity. Error analysis identifies key failure mechanisms such as cross‑round temporal misalignment and insufficient long‑range memory.
By Dewu Zheng, Yanlin Wang, Xiwen Wang, Kefeng Duan, Hongyu Zhang, Xilin Liu, Yuchi Ma, Zibin Zheng
arXiv:2607. 25873v1 Announce Type: cross Abstract: Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent.
By Ramtin Ehsani, Irene Manotas, Saurabh Pujar, Luca Buratti, Preetha Chatterjee
arXiv:2605. 17548v2 Announce Type: replace-cross Abstract: Code review has evolved for decades, from informal peer checking to today's pull request (PR) workflows, yet it remains a largely manual and cognitively demanding process.
By H\"useyin \"Ozg\"ur Kamal{\i}, Erdem Tuna, Vahid Haratian, Eray T\"uz\"un
arXiv:2608. 04682v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase.
By Haobin Li, Ping Deng, Weizhong Qian, Liang Jiang, Zhenyu Huang, Mouxing Yang, Xi Peng
arXiv:2608. 13867v1 Announce Type: cross Abstract: AI coding agents are commonly evaluated as models but deployed as systems.
By Stephanie Jarmak
arXiv:2608. 19799v1 Announce Type: new Abstract: Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions.
By Zhipeng Xu, Jiahao Lu, Yining Zheng, Yuxin Wang, Xipeng Qiu
arXiv:2609.37216v1 Announce Type: cross
Abstract: Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers...
By Yue Pan, Jiawei Li, Ziyuan Zhang, Xiangxin Zhao, He Ye
SWE‑bench Science is a benchmark for evaluating coding agents on scientific software engineering tasks, comprising 119 tasks from 98 GitHub repositories across 20 scientific domains. The tasks are grouped into Issue‑driven, Expert‑exploratory, and Engineering‑integration paradigms, and even the best agent, Claude Code with Opus‑5 (max), achieves a pass@1 below 50%. The study identifies four common failure mechanisms—lack of scientific knowledge, misguided exploration, incomplete repair coverage, and poor generalization—and shows that providing scientific guidance can both help and hinder repair depending on its alignment with the task.