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

Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand, Joey Dodds, Daniel Kroening
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:49428-49451, 2026.

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 $18.5$%.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-ibrahimzada26a, title = {{M}atch{F}ix{A}gent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair}, author = {Ibrahimzada, Ali Reza and Paulsen, Brandon and Jabbarvand, Reyhaneh and Dodds, Joey and Kroening, Daniel}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {49428--49451}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/ibrahimzada26a/ibrahimzada26a.pdf}, url = {https://proceedings.mlr.press/v306/ibrahimzada26a.html}, 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 $18.5$%.} }
Endnote
%0 Conference Paper %T MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair %A Ali Reza Ibrahimzada %A Brandon Paulsen %A Reyhaneh Jabbarvand %A Joey Dodds %A Daniel Kroening %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-ibrahimzada26a %I PMLR %P 49428--49451 %U https://proceedings.mlr.press/v306/ibrahimzada26a.html %V 306 %X 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 $18.5$%.
APA
Ibrahimzada, A.R., Paulsen, B., Jabbarvand, R., Dodds, J. & Kroening, D.. (2026). MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:49428-49451 Available from https://proceedings.mlr.press/v306/ibrahimzada26a.html.

Related Material