APPS
Canonical37papers using it
17,587HF downloads
203HF likes
2021first seen
10,000 coding problems from competitive-programming and interview sites with tests, spanning introductory to competition difficulty.
🤗 Hugging Face⚖ mit
Papers using APPS (37)
- CODESIM: Multi-Agent Code Generation and Problem Solving through
Simulation-Driven Planning and DebuggingCast a Wider Net: Coordinated Pass@K Policy Optimization for Code ReasoningPyTester: Deep Reinforcement Learning for Text-to-Testcase GenerationCODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and DebuggingARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program GenerationPrompt Optimization for LLM Code Generation via Reinforcement LearningSolvita: Enhancing Large Language Models for Competitive Programming via Agentic EvolutionAn Iterative Test-and-Repair Framework for Competitive Code GenerationSolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete ExecutionEffective Code Membership Inference for Code Completion Models via Adversarial PromptsMapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLMAlignment with Fill-In-the-Middle for Enhancing Code GenerationDr. Boot: Bootstrapping Program Synthesis Language Models to Perform RepairingAfterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency OptimizationAfterburner: Reinforcement Learning Facilitates Self-Improving Code
Efficiency OptimizationPlanning-Driven Programming: A Large Language Model Programming WorkflowMoTCoder: Elevating Large Language Models with Modular of Thought for
Challenging Programming TasksMeasuring Coding Challenge Competence With APPSCodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement LearningCodeT: Code Generation with Generated TestsCYCLE: Learning to Self-Refine the Code GenerationMapCoder: Multi-Agent Code Generation for Competitive Problem SolvingParsel: Algorithmic Reasoning with Language Models by Composing
DecompositionsFault-Aware Neural Code RankersExploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsStructCoder: Structure-Aware Transformer for Code GenerationIs Self-Repair a Silver Bullet for Code Generation?Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMsZero-Shot Detection of Machine-Generated CodesStepCoder: Improve Code Generation with Reinforcement Learning from Compiler FeedbackLess is More: Summary of Long Instructions is Better for Program
SynthesisRLTF: Reinforcement Learning from Unit Test FeedbackPerfCodeGen: Improving Performance of LLM Generated Code with Execution FeedbackUncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via
Code RewritingSelf-Explained Keywords Empower Large Language Models for Code GenerationGenX: Mastering Code and Test Generation with Execution FeedbackDemystifying GPT Self-Repair for Code Generation