DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning explores DeReason enhances reasoning in large language models through a difficulty-aware curriculum for training.. Commercial viability score: 5/10 in Reinforcement Learning.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisLearning to Reason with Curriculum I: Provable Benefits of AutocurriculumViability: 4.0
- Builds On ThisTraining Reasoning Models on Saturated Problems via Failure-Prefix ConditioningViability: 3.0
- Higher ViabilityNative Reasoning Models: Training Language Models to Reason on Unverifiable DataViability: 6.0
- Higher ViabilityOffline Exploration-Aware Fine-Tuning for Long-Chain Mathematical ReasoningViability: 7.0
- Higher ViabilityApriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning
Related Resources
- Confidence-Calibrated Reinforcement Learning(glossary)
- Multi-Agent Reinforcement Learning(glossary)
- Maximum Entropy Reinforcement Learning(glossary)
- How does PRISM improve reinforcement learning?(question)
- What is the significance of reinforcement learning in AI?(question)
- How does RetroAgent improve reinforcement learning?(question)
- Reinforcement Learning – Use Cases(use_case)