{"ID":2887056,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02611","arxiv_id":"2508.02611","title":"Meta-RAG on Large Codebases Using Code Summarization","abstract":"Large Language Model (LLM) systems have been at the forefront of applied Artificial Intelligence (AI) research in a multitude of domains. One such domain is software development, where researchers have pushed the automation of a number of code tasks through LLM agents. Software development is a complex ecosystem, that stretches far beyond code implementation and well into the realm of code maintenance. In this paper, we propose a multi-agent system to localize bugs in large pre-existing codebases using information retrieval and LLMs. Our system introduces a novel Retrieval Augmented Generation (RAG) approach, Meta-RAG, where we utilize summaries to condense codebases by an average of 79.8\\%, into a compact, structured, natural language representation. We then use an LLM agent to determine which parts of the codebase are critical for bug resolution, i.e. bug localization. We demonstrate the usefulness of Meta-RAG through evaluation with the SWE-bench Lite dataset. Meta-RAG scores 84.67 % and 53.0 % for file-level and function-level correct localization rates, respectively, achieving state-of-the-art performance.","short_abstract":"Large Language Model (LLM) systems have been at the forefront of applied Artificial Intelligence (AI) research in a multitude of domains. One such domain is software development, where researchers have pushed the automation of a number of code tasks through LLM agents. Software development is a complex ecosystem, that...","url_abs":"https://arxiv.org/abs/2508.02611","url_pdf":"https://arxiv.org/pdf/2508.02611v1","authors":"[\"Vali Tawosi\",\"Salwa Alamir\",\"Xiaomo Liu\",\"Manuela Veloso\"]","published":"2025-08-04T17:01:10Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}