What's this about?
The pipeline builds 1,648 environments across C, C++, Go and Rust, repairing sandboxes and black-box tests. Authors report Qwen3.8-27B rising from 34.87% to 42.84% after fine-tuning, with a separate agent workflow lifting performance further. Release is promised in the abstract.
What exactly is black-box test?
Checking a program’s observable inputs and outputs without requiring the same internal implementation.
What's the community saying / why does it matter?
HF: 10 upvotes; no substantive discussion collected. Separating better training data from better execution workflows helps interpret where gains come from.