Rinser is a tool developed at Amazon to ease user interaction with static analysis results presented in code reviews and is able to produce traces on average 10x shorter than Infer traces in under 6 seconds on average due the the removal of irrelevant information.
Senior engineers must verify what developers built, but evidence is buried in commit histories, too voluminous to review manually. This code is often confidential, ruling out cloud services, yet local models cannot fit a repository in context. We present an on-device Recursive Language Model (RLM) for GitHub contributi...
Christian Luis Effendy, Davin Djayadi, Pelangi Masita Wati et al.· 2026 3rd International Confe...· 0 citations
Practical static analysis of large systems such as the Linux kernel often depends on information that is difficult to capture precisely and on identifying the parts of a large codebase where precise reasoning is needed. This dissertation studies how LLMs can complement static analysis through two roles: specification r...
Hao-Nan Li· Companion Proceedings of the...· 0 citations
Structured prompting routinely improves general LLM reasoning, but whether it transfers to code generation remains underexplored even as coding tools add template layers around user requests. We compare three levels of automatically imposed prompt structure, from free-form instructions over a static component template...
Yue-Tian Mao· Proceedings of the 41st IEEE...· 0 citations
This paper focuses on four common smells and considers five prompts of diverse complexity, asking the model for detecting and removing the identified code smells, and suggests that general-purpose LLMs cannot be reliably used for that.
Giorgia Paisi, Francesca Arcelli Fontana, Bartosz Walter· WiPiEC Journal - Works in Pr...· 0 citations
We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-authored code or tests, (ii) two code-provenance tracing tools, (iii) three taxonomies for instruction intent, commit provenance, and response reliability, (iv) application of...
It is found that LLM-based approaches can generate incorrect, overspecified, or incomplete test suites in all configurations, and that the configuration has less of an effect on the generated tests than expected.
Sarah Dagger· Proceedings of the 41st IEEE...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
