The paper introduces DECODE, a dataset of 53.6K real‑world in‑IDE edits of AI‑generated code from over 1,000 developers, and uses it to study when, why, and how developers modify such code. Findings show developers spend little effort editing and often abandon AI outputs, highlighting the need for LLMs to infer intent from edits. Experiments reveal that while frontier models can generate edits that align with developer intent, they tend to over‑edit and revert changes; fine‑tuning improves performance but does not fully close the gap.
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.
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...
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.
arXiv:2607. 29516v1 Announce Type: cross Abstract: AI coding agents are generating code at volumes that exceed the capacity of traditional peer review.
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."
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).
The paper investigates how to improve confidence calibration for large language models (LLMs) used in automated code revision (ACR). It proposes applying local Platt-scaling to three fine-grained confidence scores, rather than the conventional global method, and demonstrates that this approach consistently reduces calibration error across multiple tasks, metrics, and model sizes. The study shows that fine-grained calibration, especially when combined with global scaling, yields more reliable confidence estimates for ACR tasks.
arXiv:2608. 10319v1 Announce Type: cross Abstract: Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks.
The paper compares two output regimes for code-editing language models: direct generation, where the model outputs the entire modified file, and iterative diff-based generation, where the model emits a sequence of localized edits. Experiments on Flutter/Dart tasks show that direct generation consistently outperforms diff-based generation across metrics such as compilation success, token efficiency, and quality judgments. However, diff-based generation can be competitive for short, spatially localized edits, particularly in refactoring and error-handling tasks with few edit steps.
The paper investigates the problem of over‑editing by large language models when repairing code, showing that even state‑of‑the‑art models like GPT‑5.5 frequently rewrite more code than necessary. Using a benchmark of 400 BigCodeBench problems with controlled AST corruptions, the authors quantify excess edits and demonstrate that a simple preservation instruction can reduce unnecessary changes and improve pass rates. They further explore training strategies, finding that reinforcement learning yields the best balance between edit fidelity and performance retention, highlighting edit fidelity as a distinct, measurable dimension of code‑repair quality.
arXiv:2604.20779v2 Announce Type: replace Abstract: AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful...
arXiv:2607. 05188v1 Announce Type: new Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on.