arXiv:2607. 25130v1 Announce Type: cross Abstract: Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant.
By Jenny T. Liang, Mihika Bairathi, Wayne Chi, Ameet Talwalkar, Nishant Subramani, Valerie Chen
arXiv:2509.21891v3 Announce Type: replace-cross
Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been...
By Yangtian Zi, Zixuan Wu, Aleksander Boruch-Gruszecki, Jonathan Bell, Arjun Guha
arXiv:2607. 02782v1 Announce Type: cross Abstract: Predictions by machine learning (ML) and artificial intelligence (AI) models are often received skeptically unless they are paired with intelligible explanations.
By Yalin Liu, Kosay Jabre, Rui Abreu, Zachariah J. Carmichael, Vijayaraghavan Murali, Akshay Patel, Jun Ge, Weiyan Sun, Cong Zhang, Audris Mockus, David Khavari, Peter C. Rigby, Nachiappan Nagappan
arXiv:2607. 29516v1 Announce Type: cross Abstract: AI coding agents are generating code at volumes that exceed the capacity of traditional peer review.
By Chandra Maddila, Mashrur Rashik, Euna Mehnaz Khan, Smriti Jha, James Saindon, Nachi Nagappan, Peter C. Rigby
The paper introduces CABRA, a synthetic benchmark that constructs coding tasks from scratch using call‑graph transformations and scales difficulty along four axes: function traversal, search, runtime resolution, and instruction following. Experiments with eight large language models and six coding agents on 6,840 CABRA tasks show that while LLM accuracy degrades with task size, agents maintain high performance by leveraging tools; larger tasks trigger more tool calls, and a separate study on SWE‑bench verifies that tool‑call counts better predict agent accuracy than lines of code edited. The authors argue that CABRA exposes weaknesses in LLMs that are hidden by tool use and highlights the importance of code‑understanding abilities beyond mere editing.
whyItMatters":"The study demonstrates that coding agents’ performance is more dependent on code‑understanding than on the amount of code edited, revealing a critical bottleneck for current coding agents."
By Nishant Balepur, Kiran Tomlinson, Tobias Schnabel
arXiv:2606. 08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs).
By Shi Ying Chang, Chiok Yew Ho, Yichen Li, Yintong Huo