LocalizeAgent

An evidence-grounded agent for localizing design issues in Java programs using structured program facts and iterative reasoning.

First author ICSE 2025 Program analysis + LLM

LocalizeAgent investigates design-issue localization as an evidence-grounded reasoning task. It combines structured program facts with iterative LLM reasoning so each localization claim can be traced back to concrete code evidence.

Problem

Design issues such as misplaced responsibilities and weak cohesion are diffuse and context dependent. Without structured program evidence, LLM localizations can appear plausible while remaining weakly anchored in the code.

Approach

LocalizeAgent extracts dependency graphs, call graphs, responsibility profiles, and coupling signals, then uses an iterative agent loop to reason over those facts and refine the suspected fault location.

Results

On real-world Java refactoring data, LocalizeAgent reports relative exact-match accuracy gains of 138%, 166%, and 206% for information hiding, complexity, and modularity issues, respectively.

Why it matters

Evidence-grounded localization provides a stronger basis for downstream refactoring because the agent's recommendation is connected to explicit program facts.

The full method, evaluation, and results are in the paper (Batole et al., 2025).

References

2025

  1. An LLM-Based Agent-Oriented Approach for Automated Code Design Issue Localization
    Fraol Batole, David OBrien, Tien N. Nguyen, and 2 more authors
    In 2025 IEEE/ACM 45th International Conference on Software Engineering (ICSE), Jun 2025