InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
REC RL improves LLM code generation by automatically assessing and optimizing requirement difficulty with adaptive curriculum sampling, yielding 1.23-5.62% Pass@1 gains over baselines.
abcoder-ts-parser builds reliable function-level code indexes for large TypeScript repositories significantly faster by using the compiler's native AST and semantic resolution instead of per-symbol language server calls.
PseudoBridge uses LLM-synthesized pseudo-code to bridge NL semantics and PL logic plus logic-invariant style augmentation to boost robustness and generalization in code retrieval.
citing papers explorer
-
SWE-QA: Can Language Models Answer Repository-level Code Questions?
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
-
PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval
PseudoBridge uses LLM-synthesized pseudo-code to bridge NL semantics and PL logic plus logic-invariant style augmentation to boost robustness and generalization in code retrieval.