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
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3roles
method 1polarities
use method 1representative citing papers
Open-source AI model development shows far less collaboration and openness than classic open-source software; users innovate by adapting models rather than improving them.
Fine-tuned decoder-only LLMs fall into a Semantic Trap on vulnerability detection, achieving high scores on unpaired normal code but failing on paired vulnerable-patched code, semantic perturbations, and gap analysis, while reasoning supervision reduces symptoms at the cost of recall.
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.
-
From OSS to Open Source AI: an Exploratory Study of Collaborative Development Paradigm Divergence
Open-source AI model development shows far less collaboration and openness than classic open-source software; users innovate by adapting models rather than improving them.
-
Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
Fine-tuned decoder-only LLMs fall into a Semantic Trap on vulnerability detection, achieving high scores on unpaired normal code but failing on paired vulnerable-patched code, semantic perturbations, and gap analysis, while reasoning supervision reduces symptoms at the cost of recall.