EffiHolmes: Differential Profiling-Guided Repository Level Time Inefficiency Fix Localization
TL;DR
EffiHolmes is an LLM-based frame- work for localizing fix locations of repository-level time inefficiency issues, which outperforms state-of-the-art retrieval-based, agent-based, and profiling-based baselines and remains robust across model capacities.
Abstract
Large software systems often suffer from time inefficiencies, leading to excessive execution time despite functional correctness. Local- izing the fix locations of such inefficiency issues is notoriously difficult. Applying existing fault localization paradigms to this task presents significant challenges. Unlike functional bugs, time ineffi- ciencies do not cause crashes or test failures. They therefore provide neither binary oracles nor stack-trace localization clues, making traditional fault localization and recent LLM-based methods not ap- plicable. While runtime profiling provides alternative clues, it faces some challenges in repository-level settings. Single-run profiling is non-discriminative, failing to distinguish inefficiency hotspots (i.e., time-consuming functions) from execution noise. Furthermore, existing profilers struggle to extract the execution paths relevant to inefficiency from the vast background execution. Crucially, even with the extracted execution paths, a semantic gap still persists between the observed inefficiency and where to fix. In this paper, we propose EffiHolmes, an LLM-based frame- work for localizing fix locations of repository-level time inefficiency issues. First, it employs differential profiling (default vs. scaled workloads) to pinpoint inefficiency hotspots. Second, to extract the execution paths relevant to inefficiency, it performs execution path extraction, constructing compact execution paths that connect hotspots to the reported inefficient function. Third, to bridge the gap between the hotspots and fix locations, it employs guided LLM reasoning with domain heuristics to locate the inefficiency logic. To facilitate the evaluation, we introduce RepoEffi-Bench, the first benchmark for repository-level inefficiency localization, consisting of 140 high-quality time inefficiency issues collected from popular Python repositories. The results show that EffiHolmes consis- tently outperforms state-of-the-art retrieval-based, agent-based, and profiling-based baselines, with gains of 4.29 pp on GPT-5.1 file- level Acc@3 and 15.00 pp on qwen3-4b function-level Acc@5 over the best baseline. It also remains robust across model capacities.