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.
@article{arxiv.2602.19407,
title = {Multi-CoLoR: Context-Aware Localization and Reasoning across Multi-Language Codebases},
author = {Indira Vats and Sanjukta De and Subhayan Roy and Saurabh Bodhe and Lejin Varghese and Max Kiehn and Yonas Bedasso and Marsha Chechik},
journal= {arXiv preprint arXiv:2602.19407},
year = {2026}
}
Comments
This paper has been accepted for publication at the 33rd IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER 2026)