Adversarial Agent Collaboration for C to Rust Translation

Tianyu Li, Ruishi Li, Bo Wang, Brandon Paulsen, Umang Mathur, Prateek Saxena

Keywords: Automatic Program Translation, Code Generation, Program Synthesis, LLM Agents

Abstract:

Translating C to memory-safe languages, like Rust, prevents critical memory safety vulnerabilities that are prevalent in legacy C software.
Existing approaches for C to safe Rust translation, including LLM-assisted ones, do not generalize on larger ($> 500$ LoC) C codebases because they depend on complex program analyses that frequently break.
In this work, we present ACToR (**A**dversarial **C** **To** **R**ust translator), a simple LLM agent-based approach.
Inspired by GANs, ACToR pits a generator agent against a discriminator agent, which collaborate to iteratively generate a Rust translation.
On each iteration, the translator agent synthesizes and refines a Rust translation to pass an existing suite of tests, and then the discriminator agent finds new failing tests.
We demonstrate that ACToR translates all of the 63 real-world command-line utilities considered in our benchmarks, which have an average size of 473 lines of code, and it achieves over 90\% test pass rate with zero human intervention during translation.
To our knowledge, it is the first work to show evidence that an agent-centric approach can reliably and automatically convert standalone command-line C programs at this scale.
Furthermore, ACToR improves translation correctness by up to 25.1\% compared to baseline, non-adversarial approaches.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 23884