Automated Testing and Repair for Verified Compilers Generated by a Coding Agent

• URL: http://arxiv.org/abs/2607.28928v1
• Date: Fri, 31 Jul 2026 01:04:24 GMT
• Title: Automated Testing and Repair for Verified Compilers Generated by a Coding Agent
• Abstract summary: We present an agent based automated testing and repair system for verified compilers.<n>We present specialized defect detection techniques that exploit the structure present in such compilers.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an agent based automated testing and repair system for verified compilers that contain four kinds of code: verified code, checked code, unverified code, and specification. We present specialized defect detection techniques that exploit the structure present in such compilers. For each surfaced defect the system invokes a coding agent to repair the defect and validate the repair. We evaluate the system on the Axon compiler, a compiler completely generated by a coding agent operating under developer supervision. The compiler was validated during development on a small benchmark set (the Livermore benchmarks), raising the possibility that its coding agent reward hacked the compiler. We also evaluate the possibility that the repair system reward hacked the repairs and find no evidence of reward hacking in either the Axon compiler or the repairs. We present results that characterize the testing and repair effectiveness and discuss repair characteristics.

Related papers

• Recompilation Is Not Enough: Test-Guided Decompiled-C Repair [4.193403311740078]
  Decompiled C often becomes recompilable only after repair, but recompilation alone does not establish test-observed behavior.<n>We present a few-step workflow for repairing decompiled C using compiler feedback and related official tests.
  arXiv  Detail & Related papers  (2026-09-07T08:24:53Z)
• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair [10.709112246848058]
  Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities.<n>Most existing systems treat vulnerability repair as a single generation step over the currently visible code context.<n>We present MemRepair, a memoryaugmented agentic framework that formulates vulnerability repair as an iterative, experience-driven process.
  arXiv  Detail & Related papers  (2026-05-17T13:29:46Z)
• QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization [50.722636027998]
  Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing.<n>We propose PRepair, a framework that mitigates over-editing and improves repair accuracy.
  arXiv  Detail & Related papers  (2026-04-07T14:56:38Z)
• Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair [2.267311896805228]
  Linux kernel fixes undergo iterative revision on mailing lists before acceptance, with reviewer feedback shaping correctness, handling, and API compliance.<n>We present a large-scale study of kernel patch evolution, reconstructing 6946 syzbot-linked bug-fix lifecycles.<n>We develop PatchAdvisor, a repair framework that integrates retrieval-based memory with a fine-tuned diagnostic advisor to guide a coding agent toward reviewer-aligned patches.
  arXiv  Detail & Related papers  (2026-04-04T20:23:32Z)
• RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents [70.24175620901538]
  Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters.<n>Current static safety benchmarks and red-teaming tools are inadequate for identifying emerging real-world risky scenarios.<n>We propose RedCodeAgent, the first automated red-teaming agent designed to systematically uncover vulnerabilities in diverse code agents.
  arXiv  Detail & Related papers  (2025-10-02T22:59:06Z)
• Automated Code Repair for C/C++ Static Analysis Alerts [1.260797434681533]
  Static analysis (SA) tools produce many diagnostic alerts indicating that source code in C or C++ may be defective.<n>This paper details the application of design, development, and performance testing to an APR tool we built that repairs C/C++ code associated with 3 categories of alerts produced by multiple SA tools.
  arXiv  Detail & Related papers  (2025-08-04T18:44:50Z)
• RedCode: Risky Code Execution and Generation Benchmark for Code Agents [50.81206098588923]
  RedCode is a benchmark for risky code execution and generation. RedCode-Exec provides challenging prompts that could lead to risky code execution. RedCode-Gen provides 160 prompts with function signatures and docstrings as input to assess whether code agents will follow instructions.
  arXiv  Detail & Related papers  (2024-11-12T13:30:06Z)
• Investigating the Transferability of Code Repair for Low-Resource Programming Languages [57.62712191540067]
  Large language models (LLMs) have shown remarkable performance on code generation tasks. Recent works augment the code repair process by integrating modern techniques such as chain-of-thought reasoning or distillation. We investigate the benefits of distilling code repair for both high and low resource languages.
  arXiv  Detail & Related papers  (2024-06-21T05:05:39Z)
• INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair [42.5403218101046]
  INTERVENOR is a system designed to emulate the interactive code repair processes observed in humans. LLMs play distinct roles during the code repair process, functioning as both a Code Learner and a Code Teacher.
  arXiv  Detail & Related papers  (2023-11-16T12:55:20Z)
• 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.