{"ID":5438747,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T08:54:25.326461322Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31368","arxiv_id":"2606.31368","title":"MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale","abstract":"Modern large-scale software systems often suffer from pervasive memory inefficiencies (e.g., bloat, churn), leading to excessive resource costs and performance degradation. Existing optimization workflows lack end-to-end automation, forcing developers to manually synthesize complex tool outputs into actionable and semantics-preserving fixes, precluding scalability in large codebases. To address this, this paper presents MOA, an LLM-driven framework that automatically detects and repairs recurring memory inefficiencies across production-scale codebases. Specifically, MOA operates through three agents: an Analyzer that mines anti-patterns from profiling data, a Checker Generator that synthesizes static analyzers through template-guided refinement, and a Patcher that generates optimization patches via state-machine-driven workflows. Our evaluation on OpenHarmony, an open-source operating system with over 100 million lines of C/C++ code, shows that MOA identifies 13 anti-patterns (9 previously unknown) from 3 profiled services, detects over 10,000 inefficiencies across a broader set of 7 services, and generates 769 patches with 92.5% expert acceptance rate, achieving 42.2% heap reduction and 10.6% binary size reduction on average. We envision MOA as a valuable tool for performance engineering at production scale.","short_abstract":"Modern large-scale software systems often suffer from pervasive memory inefficiencies (e.g., bloat, churn), leading to excessive resource costs and performance degradation. Existing optimization workflows lack end-to-end automation, forcing developers to manually synthesize complex tool outputs into actionable and sema...","url_abs":"https://arxiv.org/abs/2606.31368","url_pdf":"https://arxiv.org/pdf/2606.31368v1","authors":"[\"Jiaxi Liang\",\"Yuanxiang Shi\",\"Zezhou Yang\",\"Chenxiong Qian\"]","published":"2026-06-30T09:00:31Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\"]","has_code":false}