AIBullisharXiv – CS AI · Jun 236/10
🧠
From Fragments to Paths: Task-Level Context Recovery for Large Industrial Codebases
Researchers introduce DeepDiscovery, an AI method that improves how large language models understand complex industrial codebases by recovering task-relevant context across multi-relational repository structures. The system demonstrates significant performance improvements on software engineering tasks, achieving 78.6% solve rate on SWE-bench Verified and gains of 1.6-9.2 percentage points in real production environments.