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

• URL: http://arxiv.org/abs/2509.16187v1
• Date: Fri, 19 Sep 2025 17:46:13 GMT
• Title: MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
• Abstract summary: Code translation transforms source code from one programming language (PL) to another.<n>Existing automated validation and repair approaches struggle to generalize to many PLs due to high engineering overhead.<n>We develop MatchFixAgent, a large language model (LLM)-based, PL-agnostic framework for equivalence validation and repair of translations.
• Score: 5.451770256943523
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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. 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. Then it feeds this analysis to test agent to write and execute tests. Upon observing a test failure, the repair agent attempts to fix the translation bug. The final (in)equivalence decision is made by the verdict agent, considering semantic analyses and test execution results. We compare MatchFixAgent's validation and repair results with four repository-level code translation techniques. We use 2,219 translation pairs from their artifacts, which cover 6 PL pairs, and are collected from 24 GitHub projects totaling over 900K lines of code. 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%. This demonstrates that MatchFixAgent is far more adaptable to many PL pairs than prior work, while producing highly accurate validation results.

Related papers

• ExecCritic: Learn to Test, Test to Improve for Coding Agents [68.42713285082912]
  Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue.<n>We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement learning recipe for training agents within it.<n>The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests.
  arXiv  Detail & Related papers  (2026-09-08T17:53:37Z)
• Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes [55.114939648705395]
  Large language models (LLMs) have made automated program repair increasingly practical for real-world bugs.<n>Bug reproduction tests (BRTs) help close this gap by turning a bug report into an executable, bug-specific signal.<n>We propose CoHarden, a co-generation framework that uses the Lax signal as an in-loop convergence criterion.
  arXiv  Detail & Related papers  (2026-07-22T07:30:07Z)
• Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence [56.25095230687242]
  Coding agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks.<n>This problem is especially acute in conversion, where prior evaluation is outcome-driven.<n>Across blind conversion attempts, the best system reaches 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%.<n>This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.
  arXiv  Detail & Related papers  (2026-05-27T19:57:15Z)
• ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse [10.503895811137095]
  Large language model (LLM) agents are increasingly used for automated vulnerability repair.<n>Recent empirical results show that these agents still struggle with real-world vulnerabilities.<n>We present ContraFix, an agentic framework that couples runtime evidence with reusable repair skills.
  arXiv  Detail & Related papers  (2026-05-17T13:48:25Z)
• ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories [5.72515320527179]
  ReCodeAgent is an autonomous multi-agent approach for language-agnostic repository-level code translation and validation.<n>We compare the effectiveness of ReCodeAgent with four alternative neuro-symbolic and agentic approaches to translate 118 real-world projects.
  arXiv  Detail & Related papers  (2026-04-08T17:54:08Z)
• HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam [63.84155758655084]
  Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models.<n>We introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy.<n>We evaluate seven state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points.
  arXiv  Detail & Related papers  (2026-02-15T02:50:15Z)
• BabelCoder: Agentic Code Translation with Specification Alignment [7.64108921132755]
  We introduce BabelCoder, an agentic framework that performs code translation by decomposing the task into specialized agents for translation, testing, and refinement.<n>BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%.
  arXiv  Detail & Related papers  (2025-12-07T15:57:54Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)
• Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair [6.60715519922201]
  Repairing multi-hunk bugs requires coordinated edits across multiple, disjoint code regions.<n>We evaluate coding agents (Claude Code, Codex, Gemini-cli, and Qwen Code) on 372 multi-hunk bugs from the Hunk4J dataset.
  arXiv  Detail & Related papers  (2025-11-14T07:00:47Z)
• EffiReasonTrans: RL-Optimized Reasoning for Code Translation [48.862761776440635]
  EffiReasonTrans is a training framework designed to improve translation accuracy while balancing inference latency.<n>EffiReasonTrans consistently improves translation accuracy (up to +49.2% CA and +27.8% CodeBLEU compared to the base model) while reducing the number of generated tokens.
  arXiv  Detail & Related papers  (2025-10-21T17:55:39Z)
• SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair [0.0]
  We present SecureFixAgent, a hybrid repair framework integrating Bandit with lightweight local LLMs.<n>To improve precision, we apply parameter-efficient LoRA-based fine-tuning on a diverse, curated dataset.<n> Experiments show SecureFixAgent reduces false positives by 10.8% over static analysis, improves fix accuracy by 13.51%, and lowers false positives by 5.46% compared to pre-trained LLMs.
  arXiv  Detail & Related papers  (2025-09-18T15:45:43Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• RepoTransAgent: Multi-Agent LLM Framework for Repository-Aware Code Translation [6.2036957709296665]
  RepoTransAgent is a novel multi-agent framework for repository-aware code translation.<n>We evaluate RepoTransAgent on hundreds of Java-C# translation pairs from six popular open-source projects.
  arXiv  Detail & Related papers  (2025-08-25T06:56:22Z)
• Guided Debugging of Auto-Translated Code Using Differential Testing [9.897793495754225]
  tHinter is a tool to locate translation errors in auto-translated code.<n>It employs fuzzing to generate diverse test cases that thoroughly explore the translated code.<n>It then relies on a algorithm to pinpoint translation errors from coverage information and differential testing execution results.
  arXiv  Detail & Related papers  (2025-01-16T11:27:25Z)
• AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation [5.269923665485903]
  We propose AlphaTrans, a neuro-symbolic approach to automate repository-level code translation.<n>We leveraged AlphaTrans to translate ten real-world open-source projects consisting of 836, 8575, 2719> classes, methods, and tests.
  arXiv  Detail & Related papers  (2024-10-31T16:46:52Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)
• Machine Translation Models are Zero-Shot Detectors of Translation Direction [46.41883195574249]
  Detecting the translation direction of parallel text has applications for machine translation training and evaluation, but also has forensic applications such as resolving plagiarism or forgery allegations.<n>In this work, we explore an unsupervised approach to translation direction detection based on the simple hypothesis that $p(texttranslation|textoriginal)>p(textoriginal|texttranslation)$, motivated by the well-known simplification effect in translationese or machine-translationese.
  arXiv  Detail & Related papers  (2024-01-12T18:59:02Z)
• Break-It-Fix-It: Unsupervised Learning for Program Repair [90.55497679266442]
  We propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas. We use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. BIFI outperforms existing methods, obtaining 90.5% repair accuracy on GitHub-Python and 71.7% on DeepFix.
  arXiv  Detail & Related papers  (2021-06-11T20:31:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.