CodeContests
Canonical35papers using it
2022first seen
Competitive-programming problems (used to train AlphaCode) with extensive tests for code generation.
Papers using CodeContests (35)
- CODESIM: Multi-Agent Code Generation and Problem Solving through
Simulation-Driven Planning and DebuggingCodeContests+: High-Quality Test Case Generation for Competitive
ProgrammingCodeContests+: High-Quality Test Case Generation for Competitive ProgrammingCast a Wider Net: Coordinated Pass@K Policy Optimization for Code ReasoningCODESIM: 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 GenerationACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference OptimizationSolvita: 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 Execution$V_1$: Unifying Generation and Self-Verification for Parallel ReasonersSEMAG: Self-Evolutionary Multi-Agent Code GenerationCodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case GenerationDynamic Stability of LLM-Generated CodeMapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLMLogiCase: Effective Test Case Generation from Logical Description in Competitive ProgrammingSynthesizing Performance Constraints for Evaluating and Improving Code EfficiencyOpenCodeReasoning: Advancing Data Distillation for Competitive CodingBigO(Bench) -- Can LLMs Generate Code with Controlled Time and Space
Complexity?Planning-Driven Programming: A Large Language Model Programming WorkflowMoTCoder: Elevating Large Language Models with Modular of Thought for
Challenging Programming TasksCodeT: Code Generation with Generated TestsMapCoder: Multi-Agent Code Generation for Competitive Problem SolvingCode Generation with AlphaCodium: From Prompt Engineering to Flow EngineeringThink Outside the Code: Brainstorming Boosts Large Language Models in
Code GenerationZero-Shot Detection of Machine-Generated CodesLess is More: Summary of Long Instructions is Better for Program
SynthesisALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle VerifiersEnhancing Large Language Models in Coding Through Multi-Perspective
Self-ConsistencyTraining Language Models on Synthetic Edit Sequences Improves Code
SynthesisCodeTree: Agent-guided Tree Search for Code Generation with Large Language ModelsExplaining Competitive-Level Programming Solutions using LLMsDistilling Algorithmic Reasoning from LLMs via Explaining Solution
ProgramsTop Pass: Improve Code Generation by Pass@k-Maximized Code RankingPERC: Plan-As-Query Example Retrieval for Underrepresented Code
Generation