2026 · Preprint
LLM Agent-Assisted Reverse Engineering with Quantitative Readability Metrics
Uses a composite Quantitative Readability Score (QRS) to guide agents refining decompiled C. Lexical familiarity, structural simplicity and coding idioms are combined with a binary-structure similarity gate. Experiments compare refinement with and without shell access on 210 simple C binaries.
Scope and limitations
Structural similarity does not prove semantic equivalence. QRS both guides and evaluates refinement; human readability validation remains future work. The selected synthetic corpus limits generalization. Recovering compilable, behaviorally correct code from difficult binaries is outside the claimed contribution.
Why it fits this collection
Connects agent feedback design with the readability of recovered code.
Publication and review details
- Venue
- arXiv
- Status
- Preprint
- Publication / posting date
- June 5, 2026
- Date source
- arXiv v1 submission date.
- First arXiv submission
- June 5, 2026
- arXiv
- 2606.06838
- Reviewed arXiv version
- v1
Reviewed the v1 abstract and full HTML. No implementation artifact identified; experiments were not rerun.
Sources reviewed
Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.