20 results for “code changes”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper evaluates the ability of language models to reason about code changes and their semantic effects.
This paper examines the instruction stacks of five coding agents to understand their composition and evolution.
The authors argue that coding agents can replace traditional human code review in software development.
This paper proposes source code algebra as an alternative to text editing for modifying source code, allowing agents to make semantic changes with fewer tokens and higher success rates.
This paper investigates the distribution of licenses in software projects and their impact on project activity.
Nils Loose, Joseph Bienhüls, Kristoffer Hempel, Felix Mächtle +1 more
The paper evaluates code language model-based detection of vulnerability-fixing commits (VFCs) using a unified benchmark and concludes that code changes alone are insufficient for accurate detection,…
This paper investigates and compares the effectiveness of three change impact recommendation techniques for JavaScript applications.
Alex Mathai, Shobini Iyer, Aleksandr Nogikh, Petros Maniatis +3 more
This paper introduces TRIM, an algorithm that minimizes redundant edits in AI-generated code, called CodeSlop, by minimizing agent trajectories, reducing CodeSlop by 17.9%-32.9% with negligible perfor…
Ningzhi Tang, Chaoran Chen, Gelei Xu, Yiyu Shi +4 more
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system…
Guoxiang, Guo, Kla Tantithamthavorn, Neelofar Neelofar +2 more
This paper introduces CodeChat-Eval, an evaluation framework for assessing the functional correctness of Large Language Models in multi-turn code refinement dialogues.
This paper uses large language models to improve the best-known bounds for binary linear codes.
Minor, single-character perturbations to prompts can significantly degrade the security of code generated by LLMs, suggesting that prompt fragility is a major security concern beyond simple prompt inj…
Elad Sharony, Ido Greenberg, Jialin Song, Shie Mannor +2 more
CodeTriage, a learned policy, prioritizes edits before generating and testing revised code to improve efficiency in large language model code-repair systems.
Fuwei Zhang, Yanzhao Zhang, Mingxin Li, Dingkun Long +4 more
This paper introduces CORE-Bench, a comprehensive benchmark for code retrieval in agentic coding.
Jun Zhang, JianYing Qu, Hanwen Du, Zhongkai Sun +2 more
The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.
This paper characterizes oracle signals in test files of agent-authored pull requests and assesses their impact on merge outcomes.
This paper proposes a change-impact-analysis tool that fuses semantic and structural signals to identify impacted artifacts.
Han Dai, Soumyakant Priyadarshan, Abdullah Imran, Ruoyu Wang +1 more
SCRIBE is a novel framework that enables reliable source-level patching of binaries by performing 'binary-aware' recompilation, successfully resolving syntactic and semantic inaccuracies inherent in d…