Kuna: Decompiler Development in the Age of Coding Agents
A researcher has developed 'Kuna,' an experimental decompiler that utilizes LLMs to autonomously refine its code structure. The tool achieves performance levels comparable to industry standards like IDA Pro by learning from its own errors and existing decompilation frameworks.
Why it matters
This demonstrates a shift in software engineering where AI agents can autonomously improve complex, specialized tools, potentially accelerating scientific research and reverse engineering.
Today, I’m releasing Kuna , an experimental decompiler I’ve been developing over the summer while working as a visiting faculty researcher at the Air Force Research Lab (AFRL) and a research fellow at Metalware . However, when I say that I have been developing , I should clarify that an LLM has written nearly every line of code in this project.
Yet, as it stands now, this decompiler rivals the industry standard, IDA Pro (9.2), in control flow structuring on C programs: in recent benchmark results , Kuna achieves perfect structuring on 44.4% of functions, compared with IDA’s 45.7%. This was largely achieved through autonomous refinement: the LLM studies examples where it performs worse than IDA Pro on fundamental metrics, which have only emerged over the last few years . Using this strategy, it can effectively learn how another decompiler solves a hard problem through trial and error.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in