About Me

Selected Publications (view all)

1. ASE’26

   

   ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories

   Ali Reza Ibrahimzada, Brandon Paulsen, Daniel Kroening and Reyhaneh Jabbarvand

   In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE’26), October 12-16, 2026, Munich, Germany 4 citations

   Abstract

   Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs. Programming agents can enable PL-agnosticism in repository-level code translation and validation: they can synthesize code across many PLs and autonomously use existing tools specific to each PL’s analysis. However, state-of-the-art has yet to offer a fully autonomous agentic approach for repository-level code translation and validation of large-scale programs. This paper proposes ReCodeAgent, an autonomous multi-agent approach for language-agnostic repository-level code translation and validation. Users only need to provide the project in the source PL and specify the target PL for ReCodeAgent to automatically translate and validate the entire repository. ReCodeAgent is the first technique to achieve high translation success rates across many PLs. We compare the effectiveness of ReCodeAgent with four alternative neuro-symbolic and agentic approaches to translate 118 real-world projects, with 1,975 LoC and 43 translation units for each project, on average. The projects cover 6 PLs and 4 PL pairs. Our results demonstrate that ReCodeAgent consistently outperforms prior techniques on translation correctness, improving test pass rate by 60.8% on ground-truth tests, with an average cost of $15.3. We also perform process-centric analysis of ReCodeAgent trajectories to confirm its procedural efficiency. Finally, we investigate how the design choices (a multi-agent vs. single-agent architecture) influence ReCodeAgent performance: on average, the test pass rate drops by 40.4%, and trajectories become 28% longer and persistently inefficient.

   BibTeX

   @article{ibrahimzada2026recodeagent,
     title={ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories},
     author={Ibrahimzada, Ali Reza and Paulsen, Brandon and Kroening, Daniel and Jabbarvand, Reyhaneh},
     journal={arXiv preprint arXiv:2604.07341},
     year={2026}
   }

   arXiv DOI PDF Code
2. ICML’26

   MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair

   Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand, Joey Dodds and Daniel Kroening

   In Proceedings of the 43rd International Conference on Machine Learning (ICML’26), July 6-11, 2026, Seoul, South Korea 11 citations

   Abstract

   Code translation transforms source code from one programming language (PL) to another. Validating the functional equivalence of translation and repairing, if necessary, are critical steps in code translation. Existing automated validation and repair approaches struggle to generalize to many PLs due to high engineering overhead, and they rely on existing and often inadequate test suites, which results in false claims of equivalence and ineffective translation repair. To bridge this gap, we develop MatchFixAgent, a large language model (LLM)-based, PL-agnostic framework for equivalence validation and repair of translations. MatchFixAgent features a multi-agent architecture that divides equivalence validation into several sub-tasks to ensure thorough and consistent semantic analysis of the translation. We compare MatchFixAgent’s validation and repair results with four repository-level code translation techniques. Our results demonstrate that MatchFixAgent produces (in)equivalence verdicts for 99.2% of translation pairs, with the same equivalence validation result as prior work on 72.8% of them. When MatchFixAgent’s result disagrees with prior work, we find that 60.7% of the time MatchFixAgent’s result is actually correct. In addition, we show that MatchFixAgent can repair 50.6% of inequivalent translation, compared to prior work’s 18.5%.

   BibTeX

   @inproceedings{ibrahimzada2026matchfixagent,
       title={MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair},
       author={Ali Reza Ibrahimzada and Brandon Paulsen and Reyhaneh Jabbarvand and Joey Dodds and Daniel Kroening},
       booktitle={Forty-third International Conference on Machine Learning},
       year={2026},
       url={https://openreview.net/forum?id=MuyXpH3GL1}
   }

   arXiv DOI PDF Code Slides Video
3. FSE’25

   

   AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation

   Ali Reza Ibrahimzada, Kaiyao Ke, Mrigank Pawagi, Muhammad Salman Abid, Rangeet Pan, Saurabh Sinha and Reyhaneh Jabbarvand

   In Proceedings of the ACM Conference on Foundations of Software Engineering (FSE’25), June 23-27, 2025, Trondheim, Norway 104 citations

   Abstract

   Code translation transforms programs from one programming language (PL) to another. One prominent use case is application modernization to enhance maintainability and reliability. Several rule-based transpilers have been designed to automate code translation between different pairs of PLs. However, the rules can become obsolete as the PLs evolve and cannot generalize to other PLs. Recent studies have explored the automation of code translation using Large Language Models (LLMs). One key observation is that such techniques may work well for crafted benchmarks but fail to generalize to the scale and complexity of real-world projects with inter- and intra-class dependencies, custom types, PL-specific features, etc. We propose AlphaTrans, a neuro-symbolic approach to automate repository-level code translation. AlphaTrans translates both source and test code, and employs multiple levels of validation to ensure the translation preserves the functionality of the source program. To break down the problem for LLMs, AlphaTrans leverages program analysis to decompose the program into fragments and translates them in the reverse call order.We leveraged AlphaTrans to translate ten real-world open-source projects consisting of ⟨836, 8575, 2719⟩ (application and test) classes, (application and test) methods, and unit tests. AlphaTrans breaks down these projects into 17874 fragments and translates the entire repository. 96.40% of the translated fragments are syntactically correct, and AlphaTrans validates the translations’ runtime behavior and functional correctness for 27.03% and 25.14% of the application method fragments. On average, integrated translation and validation takes 34 hours (min=3, max=121) to translate a project, showing its scalability in practice. For the syntactically or semantically incorrect translations, AlphaTrans generates a report including existing translation, stack trace, test errors, or assertion failures. We provided these artifacts to two developers to fix the translation bugs in four projects. They fixed the issues in 20.1 hours on average (5.5 hours for the smallest and 34 hours for the largest project) and achieved all passing tests. Without AlphaTrans, translating and validating such big projects could take weeks, if not months.

   BibTeX

   @article{ibrahimzada2025alphatrans,
       author = {Ibrahimzada, Ali Reza and Ke, Kaiyao and Pawagi, Mrigank and Abid, Muhammad Salman and Pan, Rangeet and Sinha, Saurabh and Jabbarvand, Reyhaneh},
       title = {AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation},
       year = {2025},
       issue_date = {July 2025},
       publisher = {Association for Computing Machinery},
       address = {New York, NY, USA},
       volume = {2},
       number = {FSE},
       url = {https://doi.org/10.1145/3729379},
       doi = {10.1145/3729379},
       abstract = {Code translation transforms programs from one programming language (PL) to another. One prominent use case is application modernization to enhance maintainability and reliability. Several rule-based transpilers have been designed to automate code translation between different pairs of PLs. However, the rules can become obsolete as the PLs evolve and cannot generalize to other PLs. Recent studies have explored the automation of code translation using Large Language Models (LLMs). One key observation is that such techniques may work well for crafted benchmarks but fail to generalize to the scale and complexity of real-world projects with inter- and intra-class dependencies, custom types, PL-specific features, etc. We propose AlphaTrans, a neuro-symbolic approach to automate repository-level code translation. AlphaTrans translates both source and test code, and employs multiple levels of validation to ensure the translation preserves the functionality of the source program. To break down the problem for LLMs, AlphaTrans leverages program analysis to decompose the program into fragments and translates them in the reverse call order.We leveraged AlphaTrans to translate ten real-world open-source projects consisting of ⟨836, 8575, 2719⟩ (application and test) classes, (application and test) methods, and unit tests. AlphaTrans breaks down these projects into 17874 fragments and translates the entire repository. 96.40\% of the translated fragments are syntactically correct, and AlphaTrans validates the translations’ runtime behavior and functional correctness for 27.03\% and 25.14\% of the application method fragments. On average, integrated translation and validation takes 34 hours (min=3, max=121) to translate a project, showing its scalability in practice. For the syntactically or semantically incorrect translations, AlphaTrans generates a report including existing translation, stack trace, test errors, or assertion failures. We provided these artifacts to two developers to fix the translation bugs in four projects. They fixed the issues in 20.1 hours on average (5.5 hours for the smallest and 34 hours for the largest project) and achieved all passing tests. Without AlphaTrans, translating and validating such big projects could take weeks, if not months.},
       journal = {Proc. ACM Softw. Eng.},
       month = jun,
       articleno = {FSE109},
       numpages = {23},
       keywords = {Neuro-Symbolic Code Translation and Validation}
   }

   arXiv DOI PDF Code Slides Video
4. SCAM’25

   Challenging Bug Prediction and Repair Models with Synthetic Bugs

   Ali Reza Ibrahimzada, Yang Chen, Ryan Rong and Reyhaneh Jabbarvand

   In Proceedings of the 25th IEEE International Conference on Source Code Analysis & Manipulation (SCAM’25), September 7-12, 2025, Auckland, New Zealand 30 citations

   Abstract

   Bugs are essential in software engineering; many research studies in the past decades have been proposed to detect, localize, and repair bugs in software systems. Effectiveness evaluation of such techniques requires complex bugs, i.e., those that are hard to detect through testing and hard to repair through debugging. From the classic software engineering point of view, a hard-to-repair bug differs from the correct code in multiple locations, making it hard to localize and repair. Hard-to-detect bugs, on the other hand, manifest themselves under specific test inputs and reachability conditions. These two objectives, i.e., generating hard-to-detect and hard-to-repair bugs, are mostly aligned; a bug generation technique can change multiple statements to be covered only under a specific set of inputs. However, these two objectives conflict in the learning-based techniques: A bug should have a similar code representation to the correct code in the training data to challenge a bug prediction model to distinguish them. The hard-to-repair bug definition remains the same but with a caveat: the more a bug differs from the original code (at multiple locations), the more distant their representations are and easier to detect. This demands new techniques to generate bugs to complement existing bug datasets to challenge learning-based bug prediction and repair techniques.(p)(/p)We propose BugFarm to transform arbitrary code into multiple hard-to-detect and hard-to-repair bugs. BugFarm mutates code in multiple locations (hard-to-repair) but leverages attention analysis to only change the least attended locations by the underlying model (hard-to-detect). Our comprehensive evaluation of 435k+ bugs from over 1.9M mutants generated by BugFarm and two alternative approaches demonstrates our superiority in generating bugs that are hard to detect by learning-based bug prediction approaches (up to 40.53% higher False Negative Rate and 10.76%, 5.2%, 28.93%, and 20.53% lower Accuracy, Precision, Recall, and F1 score) and hard to repair by state-of-the-art learning-based program repair technique (28% repair success rate compared to 36% and 49% of LEAM and μBERT bugs). BugFarm is efficient, i.e., it takes nine seconds to mutate a code with no training overhead.

   BibTeX

   @INPROCEEDINGS{ibrahimzada2025challenging,
       author={Ibrahimzada, Ali Reza and Chen, Yang and Rong, Ryan and Jabbarvand, Reyhaneh},
       booktitle={2025 IEEE International Conference on Source Code Analysis & Manipulation (SCAM)}, 
       title={Challenging Bug Prediction and Repair Models with Synthetic Bugs}, 
       year={2025},
       volume={},
       number={},
       pages={133-144},
       keywords={Training;Codes;Computer bugs;Training data;Transforms;Maintenance engineering;Predictive models;Software systems;Software engineering;Testing;Bug Generation;Bug Prediction;Interpretation},
       doi={10.1109/SCAM67354.2025.00021}
   }

   arXiv DOI PDF Code Slides Video
5. ICSE’24

   

   Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code

   Rangeet Pan^*, Ali Reza Ibrahimzada^*, Rahul Krishna, Divya Sankar, Lambert Pouguem Wassi, Michele Merler, Boris Sobolev, Raju Pavuluri, Saurabh Sinha and Reyhaneh Jabbarvand

   (* equal contribution)

   In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering (ICSE ’24), April 14-20, 2024, Lisbon, Portugal 455 citations

   Abstract

   Code translation aims to convert source code from one programming language (PL) to another. Given the promising abilities of large language models (LLMs) in code synthesis, researchers are exploring their potential to automate code translation. The prerequisite for advancing the state of LLM-based code translation is to understand their promises and limitations over existing techniques. To that end, we present a large-scale empirical study to investigate the ability of general LLMs and code LLMs for code translation across pairs of different languages, including C, C++, Go, Java, and Python. Our study, which involves the translation of 1,700 code samples from three benchmarks and two real-world projects, reveals that LLMs are yet to be reliably used to automate code translation—with correct translations ranging from 2.1% to 47.3% for the studied LLMs. Further manual investigation of unsuccessful translations identifies 15 categories of translation bugs. We also compare LLM-based code translation with traditional non-LLM-based approaches. Our analysis shows that these two classes of techniques have their own strengths and weaknesses. Finally, insights from our study suggest that providing more context to LLMs during translation can help them produce better results. To that end, we propose a prompt-crafting approach based on the symptoms of erroneous translations; this improves the performance of LLM-based code translation by 5.5% on average. Our study is the first of its kind, in terms of scale and breadth, that provides insights into the current limitations of LLMs in code translation and opportunities for improving them. Our dataset—consisting of 1,700 code samples in five PLs with 10K+ tests, 43K+ translated code, 1,748 manually labeled bugs, and 1,365 bug-fix pairs—can help drive research in this area.

   BibTeX

   @inproceedings{pan2024lost,
       author = {Pan, Rangeet and Ibrahimzada, Ali Reza and Krishna, Rahul and Sankar, Divya and Wassi, Lambert Pouguem and Merler, Michele and Sobolev, Boris and Pavuluri, Raju and Sinha, Saurabh and Jabbarvand, Reyhaneh},
       title = {Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code},
       year = {2024},
       isbn = {9798400702174},
       publisher = {Association for Computing Machinery},
       address = {New York, NY, USA},
       url = {https://doi.org/10.1145/3597503.3639226},
       doi = {10.1145/3597503.3639226},
       abstract = {Code translation aims to convert source code from one programming language (PL) to another. Given the promising abilities of large language models (LLMs) in code synthesis, researchers are exploring their potential to automate code translation. The prerequisite for advancing the state of LLM-based code translation is to understand their promises and limitations over existing techniques. To that end, we present a large-scale empirical study to investigate the ability of general LLMs and code LLMs for code translation across pairs of different languages, including C, C++, Go, Java, and Python. Our study, which involves the translation of 1,700 code samples from three benchmarks and two real-world projects, reveals that LLMs are yet to be reliably used to automate code translation---with correct translations ranging from 2.1\% to 47.3\% for the studied LLMs. Further manual investigation of unsuccessful translations identifies 15 categories of translation bugs. We also compare LLM-based code translation with traditional non-LLM-based approaches. Our analysis shows that these two classes of techniques have their own strengths and weaknesses. Finally, insights from our study suggest that providing more context to LLMs during translation can help them produce better results. To that end, we propose a prompt-crafting approach based on the symptoms of erroneous translations; this improves the performance of LLM-based code translation by 5.5\% on average. Our study is the first of its kind, in terms of scale and breadth, that provides insights into the current limitations of LLMs in code translation and opportunities for improving them. Our dataset---consisting of 1,700 code samples in five PLs with 10K+ tests, 43K+ translated code, 1,748 manually labeled bugs, and 1,365 bug-fix pairs---can help drive research in this area.},
       booktitle = {Proceedings of the IEEE/ACM 46th International Conference on Software Engineering},
       articleno = {82},
       numpages = {13},
       keywords = {code translation, bug taxonomy, llm},
       location = {Lisbon, Portugal},
       series = {ICSE '24}
   }

   arXiv DOI PDF Code Slides Video
6. ICSE’24 SRC

   Program Decomposition and Translation with Static Analysis

   Ali Reza Ibrahimzada

   In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering Companion (ICSE ’24 Companion), April 14-20, 2024, Lisbon, Portugal 11 citations 🏆 Ranked 3rd in IEEE/ACM Student Research Competition at ICSE’24

   Abstract

   The rising popularity of Large Language Models (LLMs) has motivated exploring their use in code-related tasks. Code LLMs with more than millions of parameters are trained on a massive amount of code in different Programming Languages (PLs). Such models are used for automating various Software Engineering (SE) tasks using prompt engineering. However, given the very large size of industry-scale project files, a major issue of these LLMs is their limited context window size, motivating the question of "Can these LLMs process very large files and can we effectively perform prompt engineering?". Code translation aims to convert source code from one PL to another. In this work, we assess the effect of method-level program decomposition on context window of LLMs and investigate how this approach can enable translation of very large files which originally could not be done due to out-of-context issue. Our observations from 20 well-known java projects and approximately 60K methods suggest that method-level program decomposition significantly improves the limited context window problem of LLMs by 99.5%. Furthermore, our empirical analysis indicate that with method-level decomposition, each input fragment on average only consumes 5% of the context window, leaving more context space for prompt engineering and the output. Finally, we investigate the effectiveness of a Call Graph (CG) approach for translating very large files when doing method-level program decomposition.

   BibTeX

   @inproceedings{ibrahimzada2024program,
       author = {Ibrahimzada, Ali Reza},
       title = {Program Decomposition and Translation with Static Analysis},
       year = {2024},
       isbn = {9798400705021},
       publisher = {Association for Computing Machinery},
       address = {New York, NY, USA},
       url = {https://doi.org/10.1145/3639478.3641226},
       doi = {10.1145/3639478.3641226},
       abstract = {The rising popularity of Large Language Models (LLMs) has motivated exploring their use in code-related tasks. Code LLMs with more than millions of parameters are trained on a massive amount of code in different Programming Languages (PLs). Such models are used for automating various Software Engineering (SE) tasks using prompt engineering. However, given the very large size of industry-scale project files, a major issue of these LLMs is their limited context window size, motivating the question of "Can these LLMs process very large files and can we effectively perform prompt engineering?". Code translation aims to convert source code from one PL to another. In this work, we assess the effect of method-level program decomposition on context window of LLMs and investigate how this approach can enable translation of very large files which originally could not be done due to out-of-context issue. Our observations from 20 well-known java projects and approximately 60K methods suggest that method-level program decomposition significantly improves the limited context window problem of LLMs by 99.5\%. Furthermore, our empirical analysis indicate that with method-level decomposition, each input fragment on average only consumes 5\% of the context window, leaving more context space for prompt engineering and the output. Finally, we investigate the effectiveness of a Call Graph (CG) approach for translating very large files when doing method-level program decomposition.},
       booktitle = {Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings},
       pages = {453–455},
       numpages = {3},
       location = {Lisbon, Portugal},
       series = {ICSE-Companion '24}
   }

   arXiv DOI PDF Poster Slides
7. ESEC/FSE’22

   

   Perfect Is the Enemy of Test Oracle

   Ali Reza Ibrahimzada, Yigit Varli, Dilara Tekinoglu and Reyhaneh Jabbarvand

   In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE ’22), November 14–18, 2022, Singapore, Singapore 49 citations

   Abstract

   Automation of test oracles is one of the most challenging facets of software testing, but remains comparatively less addressed compared to automated test input generation. Test oracles rely on a ground-truth that can distinguish between the correct and buggy behavior to determine whether a test fails (detects a bug) or passes. What makes the oracle problem challenging and undecidable is the assumption that the ground-truth should know the exact expected, correct, or buggy behavior. However, we argue that one can still build an accurate oracle without knowing the exact correct or buggy behavior, but how these two might differ. This paper presents , a learning-based approach that in the absence of test assertions or other types of oracle, can determine whether a unit test passes or fails on a given method under test (MUT). To build the ground-truth, jointly embeds unit tests and the implementation of MUTs into a unified vector space, in such a way that the neural representation of tests are similar to that of MUTs they pass on them, but dissimilar to MUTs they fail on them. The classifier built on top of this vector representation serves as the oracle to generate “fail” labels, when test inputs detect a bug in MUT or “pass” labels, otherwise. Our extensive experiments on applying to more than 5K unit tests from a diverse set of open-source Java projects show that the produced oracle is (1) effective in predicting the fail or pass labels, achieving an overall accuracy, precision, recall, and F1 measure of 93%, 86%, 94%, and 90%, (2) generalizable, predicting the labels for the unit test of projects that were not in training or validation set with negligible performance drop, and (3) efficient, detecting the existence of bugs in only 6.5 milliseconds on average. Moreover, by interpreting the neural model and looking at it beyond a closed-box solution, we confirm that the oracle is valid, i.e., it predicts the labels through learning relevant features.

   BibTeX

   @inproceedings{ibrahimzada2022perfect,
       author = {Ibrahimzada, Ali Reza and Varli, Yigit and Tekinoglu, Dilara and Jabbarvand, Reyhaneh},
       title = {Perfect is the enemy of test oracle},
       year = {2022},
       isbn = {9781450394130},
       publisher = {Association for Computing Machinery},
       address = {New York, NY, USA},
       url = {https://doi.org/10.1145/3540250.3549086},
       doi = {10.1145/3540250.3549086},
       abstract = {Automation of test oracles is one of the most challenging facets of software testing, but remains comparatively less addressed compared to automated test input generation. Test oracles rely on a ground-truth that can distinguish between the correct and buggy behavior to determine whether a test fails (detects a bug) or passes. What makes the oracle problem challenging and undecidable is the assumption that the ground-truth should know the exact expected, correct, or buggy behavior. However, we argue that one can still build an accurate oracle without knowing the exact correct or buggy behavior, but how these two might differ. This paper presents , a learning-based approach that in the absence of test assertions or other types of oracle, can determine whether a unit test passes or fails on a given method under test (MUT). To build the ground-truth, jointly embeds unit tests and the implementation of MUTs into a unified vector space, in such a way that the neural representation of tests are similar to that of MUTs they pass on them, but dissimilar to MUTs they fail on them. The classifier built on top of this vector representation serves as the oracle to generate “fail” labels, when test inputs detect a bug in MUT or “pass” labels, otherwise. Our extensive experiments on applying to more than 5K unit tests from a diverse set of open-source Java projects show that the produced oracle is (1) effective in predicting the fail or pass labels, achieving an overall accuracy, precision, recall, and F1 measure of 93\%, 86\%, 94\%, and 90\%, (2) generalizable, predicting the labels for the unit test of projects that were not in training or validation set with negligible performance drop, and (3) efficient, detecting the existence of bugs in only 6.5 milliseconds on average. Moreover, by interpreting the neural model and looking at it beyond a closed-box solution, we confirm that the oracle is valid, i.e., it predicts the labels through learning relevant features.},
       booktitle = {Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering},
       pages = {70–81},
       numpages = {12},
       keywords = {Deep Learning, Software Testing, Test Automation, Test Oracle},
       location = {Singapore, Singapore},
       series = {ESEC/FSE 2022}
   }

   arXiv DOI PDF Code Slides Video