TRAIL runs a translator against a challenger and gains 23.1% relative syntax accuracy on C-to-Rust.

Per-trace debugging experience in agentic code translation doesn't accumulate into reusable knowledge (arXiv 2609.15381). TRAIL runs two agents adversarially, a Translator and a Challenger, distilling trace-specific experience into generalizable translation rules. Against the strongest baseline LLM translator it reports 23.1% relative improvement in syntax accuracy and 15.9% in semantic accuracy on CRUST-Bench and SmartC2Rust-Bench, and the refined insights transfer across both benchmarks.