HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithmic Coding
cs.CL, cs.AI, cs.LG
Submitted: 2025-05-30
Updated: 2026-11-08
Code: https://github.com/huggingface/open-r1
Project page: https://leililab.github.io/HardTests
Terminology
Sources
- OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Coding Challenge Competence With APPS
- ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
- TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- TACO: Topics in Algorithmic COde generation dataset
- LIMR: Less is More for RL Scaling
- Competition-Level Code Generation with AlphaCode
- Scattered Forest Search: Smarter Code Space Exploration with LLMs
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
- OpenAI o1 System Card
- Competitive Programming with Large Reasoning Models
- COFFE: A Code Efficiency Benchmark for Code Generation
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data