GraphLocator: Graph-guided Causal Reasoning for Issue Localization

2025-12-27

AI Summary

To bridge the semantic gap between natural language problem descriptions and source code localization, this paper addresses two key challenges: (1) misalignment between observed symptoms and root causes, and (2) one problem mapping to multiple dependent code entities. We propose a causal graph–guided localization method. Our core innovation is the Causal Issue Graph (CIG), which explicitly models causal dependencies between sub-problems and code entities. We further design a dynamic CIG discovery mechanism that jointly leverages program analysis, graph neural networks, and iterative graph expansion reasoning to localize symptom vertices on the repository graph and dynamically construct neighborhood-driven causal graphs. Evaluated on three real-world datasets, our method achieves +19.49% function-level recall and +11.89% precision over state-of-the-art baselines. Moreover, the generated CIGs significantly improve downstream repair task performance by 28.74%.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The issue localization task aims to identify the locations in a software repository that requires modification given a natural language issue description. This task is fundamental yet challenging in automated software engineering due to the semantic gap between issue description and source code implementation. This gap manifests as two mismatches:(1) symptom-to-cause mismatches, where descriptions do not explicitly reveal underlying root causes; (2) one-to-many mismatches, where a single issue corresponds to multiple interdependent code entities. To address these two mismatches, we propose GraphLocator, an approach that mitigates symptom-to-cause mismatches through causal structure discovering and resolves one-to-many mismatches via dynamic issue disentangling. The key artifact is the causal issue graph (CIG), in which vertices represent discovered sub-issues along with their associated code entities, and edges encode the causal dependencies between them. The workflow of GraphLocator consists of two phases: symptom vertices locating and dynamic CIG discovering; it first identifies symptom locations on the repository graph, then dynamically expands the CIG by iteratively reasoning over neighboring vertices. Experiments on three real-world datasets demonstrates the effectiveness of GraphLocator: (1) Compared with baselines, GraphLocator achieves more accurate localization with average improvements of +19.49% in function-level recall and +11.89% in precision. (2) GraphLocator outperforms baselines on both symptom-to-cause and one-to-many mismatch scenarios, achieving recall improvement of +16.44% and +19.18%, precision improvement of +7.78% and +13.23%, respectively. (3) The CIG generated by GraphLocator yields the highest relative improvement, resulting in a 28.74% increase in performance on downstream resolving task.

Problem

• Identifies code locations needing modification from issue descriptions
• Addresses semantic gaps between natural language and source code
• Mitigates symptom-to-cause and one-to-many mismatches in localization

Innovation

• GraphLocator uses causal structure discovering to mitigate symptom-to-cause mismatches.
• It employs dynamic issue disentangling to resolve one-to-many mismatches.
• The approach builds a causal issue graph for iterative reasoning over code entities.