AdverIntent-Agent: Adversarial Reasoning for Repair Based on Inferred Program Intent
Automated program repair (APR) has shown promising results, particularly with the use of neural networks. Currently, most APR tools focus on code transformations specified by test suites, rather than reasoning about the program’s intent and the high-level bug specification. Without a proper understanding of program intent, these tools tend to generate patches that overfit incomplete test suites and fail to reflect the developer’s intentions. However, reasoning about program intent is challenging. In our work, we propose an approach called AdverIntent-Agent, based on critique and adversarial reasoning. Our approach is novel to shift the focus from generating multiple APR patches to inferring multiple potential program intents. Each intent is adversarial to the others, ensuring at least one aligns closely with the developer’s original intent. AdverIntent-Agent is a multi-agent approach consisting of three agents: a reasoning agent, a test agent, and a repair agent. First, the reasoning agent generates adversarial program intents along with the corresponding faulty statements. Next, the test agent produces adversarial test cases that align with each inferred intent, constructing oracles that use the same inputs but have different expected outputs. Finally, the repair agent uses dynamic and precise LLM prompts to generate patches that satisfy both the inferred program intent and the generated tests. In this setting, each individual program intent provides ground-truth oracles that help eliminate overfitting patches. AdverIntent-Agent was evaluated on two benchmarks: Defects4J 2.0 and HumanEval-Java. AdverIntent- Agent correctly repaired the most number of bugs, 83 and 121 bugs, and achieved the highest correct (i.e. non-overfitting) rates 53.5% and 82.9% in both benchmarks, respectively. Compared to related work, AdverIntent-Agent uniquely repaired 21 and 4 bugs in two benchmarks, that had not been addressed by previous approaches, thanks to its adversarial reasoning and diversity exploration. Our work suggests a shift in developer interaction on patch acceptance by offering a comprehensive package of program intent, tests, and patches.
Wed 25 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
11:00 - 12:30 | Program RepairTool Demonstrations / Research Papers at Aurora A Chair(s): Yannic Noller Ruhr University Bochum | ||
11:00 25mTalk | LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation Research Papers Ziyao Zhang Sun Yat-sen University, Chong Wang Nanyang Technological University, Yanlin Wang Sun Yat-sen University, Ensheng Shi Xi’an Jiaotong University, Yuchi Ma Huawei Cloud Computing Technologies, Wanjun Zhong Sun Yat-sen University, Jiachi Chen Sun Yat-sen University, Mingzhi Mao Sun Yat-sen University, Zibin Zheng Sun Yat-sen University DOI | ||
11:25 25mTalk | AdverIntent-Agent: Adversarial Reasoning for Repair Based on Inferred Program Intent Research Papers He Ye University College London (UCL), Aidan Z.H. Yang Carnegie Mellon University, Chang Hu Macau University of Science and Technology, Yanlin Wang Sun Yat-sen University, Tao Zhang Macau University of Science and Technology, Claire Le Goues Carnegie Mellon University DOI | ||
11:50 25mTalk | PatchScope: LLM-Enhanced Fine-Grained Stable Patch Classification for Linux Kernel Research Papers Rongkai Liu Central South University, Heyuan Shi Central South University, Shuning Liu Central South University, China, Chao Hu Central South University, Sisheng Li Central South University, China, Yuheng Shen Tsinghua University, Runzhe Wang Alibaba Group, Xiaohai Shi Alibaba Group, Yu Jiang Tsinghua University DOI | ||
12:15 15mDemonstration | InfraFix: Technology-Agnostic Repair of Infrastructure as Code Tool Demonstrations Nuno Saavedra INESC-ID and IST, University of Lisbon, João F. Ferreira INESC-ID and IST, University of Lisbon, Alexandra Mendes Faculty of Engineering, University of Porto & INESC TEC | ||
Aurora A is the first room in the Aurora wing.
When facing the main Cosmos Hall, access to the Aurora wing is on the right, close to the side entrance of the hotel.