large reasoning models
AI models that are designed to perform complex reasoning tasks, often involving multi-step logical processes and the integration of diverse information sources. They are characterized by their large parameter sizes and extensive training data.
- A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
- Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
- Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
- CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
- Controlling Thinking Speed in Reasoning Models
- Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
- DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
- Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
- Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps
- How Far Are We from Optimal Reasoning Efficiency?
- ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests
- Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
- LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling
- Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
- Learning to Reason under Off-Policy Guidance
- Let LRMs Break Free from Overthinking via Self-Braking Tuning
- Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
- Mitigating Overthinking in Large Reasoning Models via Manifold Steering
- Multipole Attention for Efficient Long Context Reasoning
- On Reasoning Strength Planning in Large Reasoning Models
- One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
- SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
- SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
- SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
- Teaching Language Models to Reason with Tools
- The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
- Think Only When You Need with Large Hybrid-Reasoning Models
- Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
- Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
- Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms
- Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
- VeriThinker: Learning to Verify Makes Reasoning Model Efficient
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability