ScaleBox delivers a scalable code sandbox with automated special judges and parallel execution that improves verification accuracy, efficiency, and downstream RL performance on LiveCodeBench over heuristic baselines.
- If there are multiple possible solutions , print any of them
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models
ScaleBox delivers a scalable code sandbox with automated special judges and parallel execution that improves verification accuracy, efficiency, and downstream RL performance on LiveCodeBench over heuristic baselines.