New AI method ports whole C projects to Rust at 66.1% lower cost than prior work

SpeC2Rust, described in an arXiv preprint, has an AI model write specifications for each module of a C codebase, then translate and repair the code against them. All eight test projects compiled in Rust and passed their original end-to-end tests with no unsafe code. Against an earlier AI-based approach, cost fell 66.1% and input tokens 84.7%.

Photo: Fumikas Sagisavas / Wikimedia Commons, CC0 (cropped)

Sources

• Research arXiv（査読前） (2026-10-25)
  SpeC2Rust: Specification-Driven Repository-Level C-to-Rust Translation

Editorial policy ・ Terms of use