Neurosymbolic Repo-level Code Localization

TL;DR

This paper introduces LogicLoc, a novel framework combining language models and logical reasoning for accurate, verifiable code localization that overcomes superficial keyword reliance and performs well on diagnostic and real-world benchmarks.

Contribution

It formalizes the challenge of keyword-agnostic code localization, creates a diagnostic benchmark, and proposes LogicLoc, integrating LLMs with logical reasoning for improved accuracy and efficiency.

Findings

LogicLoc outperforms state-of-the-art methods on KA-LogicQuery.

LogicLoc achieves better performance with lower token use and faster execution.

State-of-the-art models struggle with structural reasoning in code localization.

Abstract

Code localization is a cornerstone of autonomous software engineering. Recent advancements have achieved impressive performance on real-world issue benchmarks. However, we identify a critical yet overlooked bias: these benchmarks are saturated with keyword references (e.g. file paths, function names), encouraging models to rely on superficial lexical matching rather than genuine structural reasoning. We term this phenomenon the Keyword Shortcut. To address this, we formalize the challenge of Keyword-Agnostic Logical Code Localization (KA-LCL) and introduce KA-LogicQuery, a diagnostic benchmark requiring structural reasoning without any naming hints. Our evaluation reveals a catastrophic performance drop of state-of-the-art approaches on KA-LogicQuery, exposing their lack of deterministic reasoning capabilities. We propose LogicLoc, a novel agentic framework that combines large language models with the rigorous logical reasoning of Datalog for precise localization. LogicLoc extracts program facts from the codebase and leverages an LLM to synthesize Datalog programs, with parser-gated validation and mutation-based intermediate-rule diagnostic feedback to ensure correctness and efficiency. The validated programs are executed by a high-performance inference engine, enabling accurate and verifiable localization in a fully automated, closed-loop workflow. Experimental results demonstrate that LogicLoc significantly outperforms SOTA methods on KA-LogicQuery while maintaining competitive performance on popular issue-driven benchmarks. Notably, LogicLoc attains superior performance with significantly lower token consumption and faster execution by offloading structural traversal to a deterministic engine, reducing the overhead of iterative LLM inference.