aiqbench analysis
This research addresses the limitations of LLM-assisted repair for decompiled C code, demonstrating that recompilation alone is insufficient to guarantee behavioral correctness without rigorous test-gate feedback. By integrating compiler diagnostics and official tests into a multi-step workflow, the study significantly improves the auditability and reliability of restoring binary functionality from decompilation artifacts. The findings highlight a critical gap in current automated repair pipelines where semantic equivalence must be verified beyond mere syntactic compilation success.
Recompilation Is Not Enough: Test-Guided Decompiled-C Repair
arXiv:2609.07201v1 Announce Type: cross Abstract: Decompiled C often becomes recompilable only after repair, but recompilation alone does not establish test-observed behavior. A recompiled command-line binary can still parse options incorrectly, print different bytes, or return a different exit status. We present a few-step workflow for repairing decompiled C using compiler feedback and related official tests. Compiler and linker diagnostics first guide build repair. Once the repaired C recompiles into a binary, smoke checks and related official tests expose behavioral discrepancies for semantic repair. In a preliminary static-enriched evaluation on 104 Coreutils 9.5 binaries with available decompiler exports and deterministic exact-output smoke comparisons, 91 binaries (87.5%) recompile and pass the test gate; 9 do not recompile within the repair budget, and 4 recompile but still fail the test gate. The result suggests that test-gate feedback can make LLM-assisted repair of decompiled C more auditable than compile-only recovery.
Abstract:Decompiled C often becomes recompilable only after repair, but recompilation alone does not establish test-observed behavior. A recompiled command-line binary can still parse options incorrectly, print different bytes, or return a different exit status. We present a few-step workflow for repairing decompiled C using compiler feedback and related official tests. Compiler and linker diagnostics first guide build repair. Once the repaired C recompiles into a binary, smoke checks and related official tests expose behavioral discrepancies for semantic repair. In a preliminary static-enriched evaluation on 104 Coreutils 9.5 binaries with available decompiler exports and deterministic exact-output smoke comparisons, 91 binaries (87.5%) recompile and pass the test gate; 9 do not recompile within the repair budget, and 4 recompile but still fail the test gate. The result suggests that test-gate feedback can make LLM-assisted repair of decompiled C more auditable than compile-only recovery.
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
arXiv:2609.07201 [cs.SE]
(or arXiv:2609.07201v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.07201 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 238 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

AutoSynthData: Generating Training Data for Enterprise Agents
Hugging Face · Oct 2, 2026

Six Principles of Voice Design: Designing for the Ear and Encoding It into Agent Script
Salesforce Blog · Oct 8, 2026
Echo: Learning-based Matching Decompilation using Trusted Back Translation
arXiv · Sep 17, 2026