A graph-integrated open-source LLM with agentless RAG resolves 43% of SWE-bench Lite issues, best among open-weight models.
Complexcodeeval: A benchmark for evaluating large code models on more complex code
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
A graph-integrated open-source LLM with agentless RAG resolves 43% of SWE-bench Lite issues, best among open-weight models.