top of page

11 items found for ""

  • Publications | AutoCodeRover

    Our Research Our research primarily focuses on automated software engineering, with a special emphasis on program repair and fuzz testing. We are proud to have our work accepted at prestigious conferences and journals in the field of software engineering. One extensively examined area is the repair of security vulnerabilities, where we strive to advance the state of the art and contribute to safer and more reliable software systems. Additionally, we have made significant contributions to the development of semantic program repair, further enhancing the effectiveness and trustworthyness of automated repair techniques. Product Autonomous Software Engineering AutoCodeRover: Autonomous Program Improvement (ISSTA24) Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, Abhik Roychoudhury ACM International Symposium on Software Testing and Analysis (ISSTA) 2024, We propose an automated approach for solving Github issues to autonomously achieve program improvement, e.g. bug fixing or feature addition. SpecRover: Code Intent Extraction via LLMs (ICSE25) Haifeng Ruan, Yuntong Zhang, Abhik Roychoudhury 47th International Conference on Software Engineering (ICSE) 2025. This study seeks to demonstrate the continued importance of specification inference in automated program repair, even as program repair technologies enter the LLM era. Works on Automatic Programming Automatic Programming: LLMs and Beyond Michael R. Lyu , Baishakhi Ray , Abhik Roychoudhury , Shin Hwei Tan , Patanamon Thongtanunam A forward-looking view, focusing on the programming environment of the near future, where programmers may need to switch to different roles to fully utilize the power of automatic programming. Automated Program Repair (CACM19) Claire Le Goues, Michael Pradel, Abhik Roychoudhury Communications of the ACM, Volume 62, Issue 12 Automated program repair is an emerging and exciting field of research that allows for automated rectification of software errors and vulnerabilities. Automated Repair of Programs from Large Language Models (ICSE23) Zhiyu Fan , Xiang Gao , Martin Mirchev , Abhik Roychoudhury , Shin Hwei Tan 45th International Conference on Software Engineering (ICSE) 2023 This study revealed that automatically generated code shares common programming mistakes with human-crafted solutions, indicating APR techniques have potential to fix auto-generated code. Product Seminal Papers in Program Repair SemFix: Program Repair via Semantic Analysis (ICSE13 Test of Time Award) Hoang Duong Thien Nguyen , Dawei Q i, Abhik Roychoudhury , Satish Chandra 35th International Conference on Software Engineering (ICSE) 2013. In this paper, an automated repair method based on symbolic execution, constraint solving and program synthesis is presented. This work has been the starting point for semantic program repair. Angelix: Scalable Multiline Program Patch Synthesis via Symbolic Analysis (ICSE16) Sergey Mechtaev ; Jooyong Yi ; Abhik Roychoudhury 38th International Conference on Software Engineering (ICSE) 2016. Ange lix is a novel semantics-based repair method that scales to industry-scale programs in C. Publications Our research primarily focuses on automated engineering, with a special emphasis on program repair fuzz testing. We are proud to have our work accepted at prestigious conferences and journals in the field of software engineering. One extensively examined area is the repair of security vulnerabilities, where we strive to advance the state of the art and contribute to safer and more reliable software systems. Additionally, we have made significant contributions to the development of semantic program repair, further enhancing the effectiveness and trustworthiness of automatedrepair techniques. Automated Vulnerability Remediation Vulnerability Repair via Inductive Inference (ISSTA22) Yuntong Zhang, Xiang Gao, Gregory J. Duck, Abhik Roychoudhury 38th International Conference on Software Engineering (ICSE) 2016. In this paper, a counter-example guided inductive inference procedure over program states to define likely invariants at possible fix locations was presented to reduce the time between reporting and fix of a vulnerability. Concolic Program Repair (PLDI21) Ridwan Shariffdeen , Yannic Noller , Lars Grunske , Abhik Roychoudhury 42nd International Conference on Programming Language Design and Implementation 2021 In this work we propose an integrated approach for detecting and discarding overfitting patches via systematic co-exploration of the patch space and input space. Program Vulnerability Repair via Crash Constraint Extraction (TOSEM21) Xiang Gao, Bo Wang, Gregory J. Duck, Ruyi Ji, Yingfei Xiong, Abhik Roychoudhury ACM Trans. Softw. Eng. Methodol., Vol. 30, No. 2, Article 14, Publication date: February 2021. In this paper, we propose a general approach to combat the over-fitting problem, specifically for fixing security vulnerabilities. Our key insight is that information about the underlying cause of a vulnerability can be automatically extracted, and this information can then be used to guide Automated Program Repair (APR).

  • AutoCodeRover | DevAssistant

    Empowering Software Evolution Our mission is to revolutionize the way enterprises and developers manage and enhance their software systems. Autonomous Program Improvement AutoCodeRover is a technology we are building for enterprises and developers to maintain reliable and performant software systems through autonomous program improvement. Research Paper 1 (ISSTA 24) Research Paper 2 (ICSE 25) Efficient & Economical Support Multiple Languages Assurance with Evidence python c cpp js ts java php go Support for Multiple Langauges AutoCodeRover agent currently supports eight mainstream programming languages, and we continue to extend support for more. Integration with Frontier Models and Foundational Models AutoCodeRover is compatible with numerous models from commercial vendors as well as various open-source models. Configuring an existing large language model or utilizing your own fine-tuned model is a straightforward process. OpenAI Anthropic Gemini AWS Bedrock LLAMA3 Azure AI

  • Team | AutoCodeRover

    Our Team We are part of the Trustworthy Software Systems group from the National University of Singapore's School of Computing. In our research, we strive to enable secure and trustworthy software systems. In line with this, we focus on software testing and analysis, and in particular have contributed to the areas of Automated Program Repair, Fuzzing, and Symbolic Execution. We believe that this knowledge can be utilized to ensure that language-model based agents can create code that developers can use with confidence. Meet The Founders Co-Founder & CEO Ridwan Shariffdeen Ridwan Shariffdeen holds a Ph.D from the National University of Singapore. He has more than 8 years of experience working in the industry and academia focusing on software security. His research focuses on software security, automated program repair, and trustworthy software systems. His research has been published in top-tier conferences and journals such as ICSE, PLDI, TOSEM, and IEEE CLOUD. He also contributes to the field of software engineering by peer reviewing for top-tier journals such as ACM TOSEM, IEEE TSE and top-tier conferences such as ICSE, ASE and FSE. Co-Founder & Co-Chief Science Officer Yuntong Zhang Yuntong Zhang is currently a third-year PhD student at National University of Singapore. He is generally interested in topics related to improving quality and security guarantees of software systems. His current research focuses on fostering evidence and practicality in automated programming, where code is generated by automated tools or machine learning models. He is actively working on Language Model agents for code generation and program improvements. Previously, he has worked on analysis-based program repair for security vulnerabilities, as well as software sanitizers for vulnerability detection. Co-Founder & Co-Chief Science Officer Haifeng Ruan Ruan Haifeng is a third-year PhD student at School of Computing, National University of Singapore. His research focuses on program testing and repair and trustworthy auto-programming. Co-Founder & CTO Martin Mirchev Martin Mirchev is currently a second-year PhD student at the National University of Singapore. He is interested in topics related to providing trust and certification guarantees of software systems. His current research focuses on providing such certifications in automated programming, where code is generated by automated tools or machine learning models. Co-Founder and Advisor Abhik Roychoudhury Abhik Roychoudhury is a Provost’s Chair Professor of Computer Science at the National University of Singapore. Abhik’s research focuses on software testing and analysis, software security and trust-worthy software construction. His research was honored with IEEE TCSE New Directions Award in 2022 (jointly with Cristian Cadar) for contributions to symbolic execution, as well as with International Conference on Software Engineering (ICSE) 2023 Most Influential Paper Award for an ICSE 2013 paper suggesting semantic approaches towards program repair. His research group is known for contributions to automatic programming, program repair, fuzzing and symbolic execution.

  • Request Source | AutoCodeRover

    Get Source Code Access First name Last name Affiliation* Job Title* Institution Email* Personal Page Give us more details* Request Access

  • Privacy Policy | WeDu

    Privacy Policy A privacy policy is a statement that discloses some or all of the ways a website collects, uses, discloses, and manages the data of its visitors and customers. It fulfills a legal requirement to protect a visitor or client's privacy. Countries have their own laws with different requirements per jurisdiction regarding the use of privacy policies. Make sure you are following the legislation relevant to your activities and location. In general, what should you cover in your Privacy Policy? What type of information do you collect? How do you collect information? Why do you collect such personal information? How do you store, use, share and disclose your site visitors' personal information? How (and if) do you communicate with your site visitors? Is your service targeting and collecting information from Minors? Privacy policy updates Contact Information You can check out this support article to receive more information about how to create a privacy policy. The explanations and information provided herein are only general explanations, information and samples. You should not rely on this article as legal advice or as recommendations regarding what you should actually do. We recommend that you seek legal advice to help you understand and to assist you in the creation of your privacy policy.

  • Join Waitlist | AutoCodeRover

    Get early access to AutoCodeRover Cloud First name Last name Email Company name Position Preferred Programming Language If Other, please specify Version Control System Bug Reporting System Join Waitlist

  • Products | AutoCodeRover

    Our Products We build cutting-edge technology for autonomous program improvement solutions that adapt to your unique business needs, driving seamless software evolution. Deployment Acceleration Our platform offers efficient workflows that streamline the process of software enhancement, allowing for greater productivity and collaboration. Assured Autonomy Trust enhancement by generating evidence of correctness. Experience the reliance of quality assurance provided with AI generated code Seamless Integrations Our platform is designed to seamlessly integrate with existing developer workflows to enhance the software development lifecycle through intelligent automation. Dynamic New Worklfows AutoCodeRover enables organizations to maintain robust and high-performance software systems with minimal human intervention. Coming Soon Join the waitlist and stay tuned for our latest product developments Cloud SaaS Seamless integration into your existing development workflows IDE Plugins Invoke AutoCodeRover while developing at your IDE GitHub Bot Autonomous agent in your GitHub issue tracker

  • Terms & Conditions | WeDu

    Terms & Conditions AutoCodeRover is a technology we are building to help enterprises maintain reliable and performant software systems through autonomous program improvement. Our terms and conditions set forth the guidelines governing the use of AutoCodeRover and the relationship between AutoCodeRover and its users. These terms are designed to protect both parties and ensure a fair and transparent usage of our platform. What should be covered in our Terms & Conditions? In our terms and conditions, we cover: The information provided here is for general understanding only and should not be considered as legal advice. We recommend seeking legal counsel to ensure compliance and understanding of our terms and conditions.

  • Careers | AutoCodeRover

    Join the Revolution: Unite Your Talent for Excellence We are Hiring! We are looking for enthusiastic and energetic people to join our team. We are a small team of researchers passionate about building the next generation of solutions to revolutionize software maintenance. We want to hire skilled people who are ambitious to collaborate in our journey to make software engineering efficient. Product Engineer We are looking for product-oriented full-stack developers to build our core product. You will be closely working with the founders as part of the core team, envisioning the next-generation AI developer. Apply Full Stack Engineer We seek a passionate full-stack engineer delivering the best user experience for cutting-edge technology. You will build the back end, which empowers the next-generation AI assistant, and the front end, which creates seamless new workflows. Apply Research Engineer We are hiring enthusiastic researchers who are seeking to take new challenges. We are looking for highly motivated engineers who are interested in building the next generation AI developer assistant. Apply

  • 404 Error Page | AutoCodeRover

    Oops, looks like this is the wrong path. Check the URL, or go back to the homepage and try again. Back to Homepage

  • Plans & Pricing | WeDu

    Explore Our Pricing Plans Use this area to describe one of your memberships. Free $ 0 0$ Use this area to describe one of your memberships. Valid for 3 months Get Started I'm a benefit I'm a benefit Standard $ 30 30$ Every month Use this area to describe one of your memberships. Valid for 6 months Get Started I'm a benefit I'm a benefit I'm a benefit Best Value Premium $ 50 50$ Every month Use this area to describe one of your memberships. Valid for 12 months Get Started I'm a benefit I'm a benefit I'm a benefit I'm a benefit

bottom of page