ACToR improves C-to-Rust translation correctness via an adversarial LLM-agent loop that generates differential fuzz tests to drive iterative refinements, achieving over 90% pass rates on 63 real-world utilities.
<...Test formatting requirements> IF {$allow_fuzz} <...Details on the usage of the fuzzer script> ENDIF ## Constraints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adversarial Agent Collaboration for Correctness Improvements of C to Safe Rust Translation
ACToR improves C-to-Rust translation correctness via an adversarial LLM-agent loop that generates differential fuzz tests to drive iterative refinements, achieving over 90% pass rates on 63 real-world utilities.