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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
citing papers explorer
-
Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning
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.
-
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.