Loop invariant inference, a key component in program verification, is a challenging task due to the inherent undecidability and complex loop behaviors in practice. Recently, machine learning based techniques have demo...
详细信息
ISBN:
(数字)9798400712487
ISBN:
(纸本)9798400712487
Loop invariant inference, a key component in program verification, is a challenging task due to the inherent undecidability and complex loop behaviors in practice. Recently, machine learning based techniques have demonstrated impressive performance in generating loop invariants automatically. However, these methods highly rely on the labeled training data, and are intrinsically random and uncertain, leading to unstable performance. In this paper, we investigate a synergy of large language models (LLMs) and bounded model checking (BMC) to address these issues. The key observation is that, although LLMs may not be able to return the correct loop invariant in one response, they usually can provide all individual predicates of the correct loop invariant in multiple responses. To this end, we propose a "query-filter-reassemble" strategy, namely, we first leverage the language generation power of LLMs to produce a set of candidate invariants, where training data is not needed. Then, we employ BMC to identify valid predicates from these candidate invariants, which are assembled to produce new candidate invariants and checked by off-the-shelf SMT solvers. The feedback is incorporated into the prompt for the next round of LLM querying. We expand the existing benchmark of 133 programs to 316 programs, providing a more comprehensive testing ground. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art techniques, successfully generating 309 loop invariants out of 316 cases, whereas the existing baseline methods are only able to tackle 219 programs at best. The code is publicly available at https://***/SoftWiser-group/***.
Large language models (LLMs) have achieved impressive performance on code generation. Although prior studies enhanced LLMs with prompting techniques and code refinement, they still struggle with complex programming pr...
详细信息
ISBN:
(数字)9798400712487
ISBN:
(纸本)9798400712487
Large language models (LLMs) have achieved impressive performance on code generation. Although prior studies enhanced LLMs with prompting techniques and code refinement, they still struggle with complex programming problems due to rigid solution plans. In this paper, we draw on pair programming practices to propose PAIRCODER, a novel LLM-based framework for code generation. PAIRCODER incorporates two collaborative LLM agents, namely a NAVIGATOR agent for high-level planning and a Driver agent for specific implementation. The NAVIGATOR is responsible for proposing promising solution plans, selecting the current optimal plan, and directing the next iteration round based on execution feedback. The DRIVER follows the guidance of NAVIGATOR to undertake initial code generation, code testing, and refinement. This interleaved and iterative workflow involves multi-plan exploration and feedback-based refinement, which mimics the collaboration of pair programmers. We evaluate PAIRCODER with both open-source and closed-source LLMs on various code generation benchmarks. Extensive experimental results demonstrate the superior accuracy of PAIRCODER, achieving relative pass@1 improvements of 12.00% 162.43% compared to prompting LLMs directly.
The ability to simulate is influenced considerably by the softwaretechnology available to the modeler. The access, availability, and use of simulation software are, in turn, affected by cost considerations, geographi...
详细信息
As the public pays more and more attention to fire, the importance of fire prevention is becoming increasingly prominent. This paper focuses on the realization of fire alarm software that can alarm in real time. Throu...
详细信息
Recent interest in integrating Internet of Things (IoT) technology with softwareengineering has grown owing to its potential to transform several fields. The purpose of this research is to review the literature that ...
详细信息
ISBN:
(纸本)9798350354140;9798350354133
Recent interest in integrating Internet of Things (IoT) technology with softwareengineering has grown owing to its potential to transform several fields. The purpose of this research is to review the literature that are related to the integration of IoT with softwareengineering and explores the opportunities, challenges, and future directions. To fulfil this objective, a total of 22 articles related to the issues were reviewed using PRISMA. The findings showed that new software developments due to cloud computing and IoT need IoT-compatible architectures. Data security, authentication, access control, and trust management take precedence. The study also reveals managerial, architectural, security, interoperability, scalability, and professional training challenges in softwareengineering using IoT technologies. Despite these challenges, IoT is changing healthcare, smart cities, and industrial automation. The findings highlight the need for interdisciplinary collaboration and particular solutions to solve IoT-softwareengineering integration issues.
Ensuring product security in software development is crucial, encompassing hardware, firmware, and holistic protection measures. With rising cyber threats, organizations face challenges in safeguarding software produc...
详细信息
Based on the current characteristics of aerospace equipment software development, this paper studies the quality improvement technology of aerospace equipment software based on the 'quality chain'. Starting fr...
详细信息
The present invention proposes a reconfigurable software design method based on design patterns for intelligent fusion terminal software in low-voltage distribution substations. The method divides each functional modu...
详细信息
software document is a file that records the composition and workflow of software, and it is an important basis for software maintenance and development. At present, we have the source program of the rCore operating s...
详细信息
暂无评论