Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair

TL;DR

This paper introduces WILLIAMT, a cost-effective and scalable automated program repair system that leverages crash-site repair and template-guided patch generation, significantly improving bug-fixing efficiency and reducing costs.

Contribution

It presents a novel crash-site repair approach combined with template-guided patch generation, reducing token costs and enabling effective bug fixing with local LLMs.

Findings

Reduces token cost by 45.9%

Increases bug-fixing rate to 73.5% on ARVO benchmark

Effective even with local models on Mac M4 Mini

Abstract

The rapid advancement of bug-finding techniques has led to the discovery of more vulnerabilities than developers can reasonably fix, creating an urgent need for effective Automated Program Repair (APR) methods. However, the complexity of modern bugs often makes precise root cause analysis difficult and unreliable. To address this challenge, we propose crash-site repair to simplify the repair task while still mitigating the risk of exploitation. In addition, we introduce a template-guided patch generation approach that significantly reduces the token cost of Large Language Models (LLMs) while maintaining both efficiency and effectiveness. We implement our prototype system, WILLIAMT, and evaluate it against state-of-the-art APR tools. Our results show that, when combined with the top-performing agent CodeRover-S, WILLIAMT reduces token cost by 45.9% and increases the bug-fixing rate to 73.5% (+29.6%) on ARVO, a ground-truth open source software vulnerabilities benchmark. Furthermore, we demonstrate that WILLIAMT can function effectively even without access to frontier LLMs: even a local model running on a Mac M4 Mini achieves a reasonable repair rate. These findings highlight the broad applicability and scalability of WILLIAMT.