o1 or r1-style LLMs, often called “large reasoning models” (LRMs) (see Cuadron 2025)

• Xu et al 2025 - Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
• Kumar et al 2025 - LLM Post-Training: A Deep Dive into Reasoning Large Language Models
• Sui et al 2025 - Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

• Havrilla et al 2024 - Teaching Large Language Models to Reason with Reinforcement Learning
• OpenAI o1
  • Learning to Reason with LLMs Has examples of the full reasoning chains.
  • OpenAI o1 System Card arXiv (There is a lot of information to be gleaned about the training process if you read section 2 carefully.)
• DeepSeek-AI et al 2025 - DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  • See also Reinforcement Learning with Verifiable Rewards
  • R1 replication on small datasets
    • Zheng et al 2025 - 7B Model and 8K Examples: Emerging Reasoning with Reinforcement Learning is Both Effective and Efficient
• General papers
  • Muennighoff et al 2025 - s1: Simple test-time scaling
  • Ye et al 2025 - LIMO: Less is More for Reasoning
  • 2025 - The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
  • Yang et al 2025 - PENCIL: Long Thoughts with Short Memory
  • Essential AI 2025 - Rethinking Reflection in Pre-Training
  • Ma et al 2025 - Reasoning Models Can Be Effective Without Thinking
  • Yang et al 2025 - Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
  • Yue et al 2025 - Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  • Tan et al 2025 - Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
• Concise Reasoning
  • Using RL
    • Song & Zheng 2025 - Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning
• Parallel and Collaborative Thinking
  • Rodionov et al 2025 - Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
  • Luo et al 2025 - Learning from Peers in Reasoning Models
• Problems and Insights
  • Qin et al 2025 - Decomposing Elements of Problem Solving: What "Math" Does RL Teach? “RL-trained models struggle with fundamentally new problems, hitting a ‘coverage wall’ due to insufficient planning skills”
• Models
  • Phi-4-Reasoning: Abdin et al 2025 - Phi-4-reasoning Technical Report
  • Chen et al 2025 - Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition Has a “fast” mode for routine queries and a deeper “slow” mode for complex inference

• Reasoning Chains
• Reinforcement Learning with Verifiable Rewards
• Test-Time Scaling