# Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures

arXiv: https://arxiv.org/abs/2512.05908 · HTML: https://mlsanity.com/paper/2512.05908/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Builds on (most cited first, 16 of 16)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [OrcaLoca: An LLM Agent Framework for Software Issue Localization](https://mlsanity.com/paper/2502.00350/) (2025)
- [GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model](https://mlsanity.com/paper/2406.07003/) (2024)
- [Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search](https://mlsanity.com/paper/2401.04514/) (2024)
- [Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent](https://mlsanity.com/paper/2008.12193/) (2020)
- [Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models](https://mlsanity.com/paper/2502.15292/) (2025)
- [LLM Agents Improve Semantic Code Search](https://mlsanity.com/paper/2408.11058/) (2024)
- [Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs](https://mlsanity.com/paper/2501.07857/) (2025)
- [Code-Craft: Hierarchical Graph-Based Code Summarization for Enhanced Context Retrieval](https://mlsanity.com/paper/2504.08975/) (2025)
- [Improving LLM-Based Fault Localization with External Memory and Project Context](https://mlsanity.com/paper/2506.03585/) (2025)
- [Meta-RAG on Large Codebases Using Code Summarization](https://mlsanity.com/paper/2508.02611/) (2025)
- [Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization](https://mlsanity.com/paper/2503.10737/) (2025)
- [Improving Source Code Similarity Detection Through GraphCodeBERT and Integration of Additional Features](https://mlsanity.com/paper/2408.08903/) (2024)

## Built on by (most cited first, 1 of 1)

- [Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study](https://mlsanity.com/paper/2608.01507/) (2026)

## Abstract (arXiv)

Bug localization in multi-repository microservice architectures is challenging due to the semantic gap between natural language bug reports and code, LLM context limitations, and the need to first identify the correct repository. We propose reframing this as a natural language reasoning task by transforming codebases into hierarchical NL summaries and performing NL-to-NL search instead of cross-modal retrieval. Our approach builds context-aware summaries at file, directory, and repository levels, then uses a two-phase search: first routing bug reports to relevant repositories, then performing top-down localization within those repositories. Evaluated on DNext, an industrial system with 46 repositories and 1.1M lines of code, our method achieves Pass@10 of 0.82 and MRR of 0.50, significantly outperforming retrieval baselines and agentic RAG systems like GitHub Copilot and Cursor. This work demonstrates that engineered natural language representations can be more effective than raw source code for scalable bug localization, providing an interpretable repository -> directory -> file search path, which is vital for building trust in enterprise AI tools by providing essential transparency.