Multi-CoLoR: Context-Aware Localization and Reasoning across Multi-Language Codebases

2026-02-22

AI Summary

This work addresses the challenge that large language models struggle to effectively locate relevant code across multilingual repositories due to a lack of understanding of organizational context and cross-language structural relationships. To this end, we propose Multi-CoLoR, a novel framework that integrates organizational knowledge—such as historical bug-fix patterns—with graph-based reasoning to enable context-aware, cross-language code localization. Our approach introduces a Similar Issue Context (SIC) module for retrieving semantically and organizationally relevant contexts and extends LocAgent to construct a graph-traversal agent capable of structured reasoning. Evaluated on real-world enterprise datasets, Multi-CoLoR significantly improves the Acc@5 metric over lexical and graph-structured baselines while reducing the number of tool invocations.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Large language models demonstrate strong capabilities in code generation but struggle to navigate complex, multi-language repositories to locate relevant code. Effective code localization requires understanding both organizational context (e.g., historical issue-fix patterns) and structural relationships within heterogeneous codebases. Existing methods either (i) focus narrowly on single-language benchmarks, (ii) retrieve code across languages via shallow textual similarity, or (iii) assume no prior context. We present Multi-CoLoR, a framework for Context-aware Localization and Reasoning across Multi-Language codebases, which integrates organizational knowledge retrieval with graph-based reasoning to traverse complex software ecosystems. Multi-CoLoR operates in two stages: (i) a similar issue context (SIC) module retrieves semantically and organizationally related historical issues to prune the search space, and (ii) a code graph traversal agent (an extended version of LocAgent, a state-of-the-art localization framework) performs structural reasoning within C++ and QML codebases. Evaluations on a real-world enterprise dataset show that incorporating SIC reduces the search space and improves localization accuracy, and graph-based reasoning generalizes effectively beyond Python-only repositories. Combined, Multi-CoLoR improves Acc@5 over both lexical and graph-based baselines while reducing tool calls on an AMD codebase.

Problem

• code localization
• multi-language codebases
• context-aware reasoning
• software repository navigation
• cross-language code retrieval

Innovation

• multi-language code localization
• context-aware reasoning
• code graph traversal
• organizational knowledge retrieval
• heterogeneous codebases