DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning
Paper
•
2504.07128
•
Published
•
86
Deep Think
-
-
BM25S: Orders of magnitude faster lexical search via eager sparse scoring
Paper • 2407.03618 • Published • 13 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 87 -
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Paper • 2508.05004 • Published • 126 -
Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards
Paper • 2507.14783 • Published • 3 -
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
Paper • 2507.10628 • Published • 1 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 183 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 189 -
Reverse-Engineered Reasoning for Open-Ended Generation
Paper • 2509.06160 • Published • 147 -
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Paper • 2509.06733 • Published • 31 -
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
Paper • 2509.03646 • Published • 30 -
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Paper • 2509.06923 • Published • 21 -
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 673 -
Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
Paper • 2509.04292 • Published • 57 -
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
Paper • 2507.04009 • Published • 48 -
Scaling Agents via Continual Pre-training
Paper • 2509.13310 • Published • 112 -
QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading
Paper • 2509.09995 • Published • 14 -
ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
Paper • 2509.13313 • Published • 78 -
PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
Paper • 2509.19894 • Published • 32 -
When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance
Paper • 2509.22193 • Published • 37