Adding 12% cross-repository code dependency contexts to the long-context fine-tuning mix improves long-range retrieval, state tracking, repo code understanding, and agentic tool use, while largely preserving short-context coding.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
Adding 12% cross-repository code dependency contexts to the long-context fine-tuning mix improves long-range retrieval, state tracking, repo code understanding, and agentic tool use, while largely preserving short-context coding.