In this paper, we pay attention to the efficiency of automated program repair (APR). Recently, an efficient patch scheduling algorithm, Casino, has been proposed to improve APR efficiency. Inspired by fuzzing, Casino adaptively chooses the next patch candidate to evaluate based on the results of previous evaluations. However, we observe that Casino utilizes only the test results, treating the patched program as a black box. Inspired by greybox fuzzing, we propose a novel patch-scheduling algorithm, Gresino, which leverages the internal state of the program to further enhance APR efficiency. Specifically, Gresino monitors the hit counts of branches observed during the execution of the program and uses them to guide the search for a valid patch. Our experimental evaluation on the Defects4J benchmark and eight APR tools demonstrates the efficacy of our approach.

In this work, we present a novel approach that connects two closely-related topics: fuzzing and automated program repair (APR). The paper is divided into two parts. In the first part, we describe the similarities between fuzzing and APR both of which can be viewed as a search problem. In the second part, we introduce a new patch-scheduling algorithm called Casino, which is designed from a fuzzing perspective to enhance search efficiency. Our experiments demonstrate that Casino outperforms existing algorithms. We also promote open science by sharing SimAPR, a simulation tool that can be used to evaluate new patch-scheduling algorithms.