Semantic navigation improves finding code for fixing issues
Semantic Navigation for Issue Localization in Code Repository
Artificial Intelligence
Summary
When programmers fix problems in software, they need to find the right files and functions in large collections of code. The authors created SemNav, a system that helps find these code parts more effectively by using a map of code relationships, summaries of each code part related to the problem, and keeping track of why each part is considered relevant. This helps the system improve its guesses about where the problem is and makes it easier for programmers to focus on important parts. Tests show SemNav finds the right files more often and helps fix issues better than previous methods.
What this means in practice
- •For software development teams: Locate and prioritize code files and functions linked to reported bugs more accurately for faster issue resolution.
- •For devops engineers: Improve debugging workflows by integrating semantic navigation to reduce code exploration time during incident investigations.
Authors
Yunxiang Wei, Zhenyu Lei, Jundong Li
Abstract
Repository-level issue localization aims to identify and rank the files and functions relevant to resolving a reported issue. LLM agents approach this task iteratively: they identify a set of potentially relevant locations, inspect the corresponding code, and revise their judgments about these candidates as new evidence is acquired. Existing environments, however, provide limited support for this loop: agents must search for unresolved relation targets, reconstruct entity semantics from raw source code, and revise candidates without evidential basis. To address these limitations, we present SemNav, a framework that leverages deterministic retrieval to seed a broad candidate set and an LLM agent to continually refine that set, thereby combining initial coverage with evidence-guided revision. SemNav supports this process through three key components. A Semantic Navigation Graph resolves program relations on demand through a language server, enabling direct navigation to related entities across files. Issue-conditioned Semantic Cards provide compact, source-grounded interpretations of each entity's role and relevance to the issue. A persistent Candidate Workspace records each candidate together with its evidential basis, enabling grounded verification, revision, and ranking. Across SWE-bench Lite and PLocBench, SemNav outperforms existing baselines, improving File Hit@10 from 68.33\% to 82.67\% with Gemma 4B. Component ablations and trajectory analysis support the complementary roles of all three components, while Semantic Cards reduce working-context load by 48.2\% relative to full-source reading. SemNav further ranks first on all seven evidence-quality metrics on SWE-Explore and improves downstream issue resolution from 44.00\% to 52.33\%.