Large Language Models Can Self-Improve in Long-context Reasoning
Paper
• 2411.08147 • Published
• 65
reasoning
-
-
Reverse Thinking Makes LLMs Stronger Reasoners
Paper • 2411.19865 • Published • 23 -
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 94 -
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
Paper • 2412.18925 • Published • 107 -
ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
Paper • 2501.06590 • Published • 11 -
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Paper • 2501.12570 • Published • 28 -
Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament
Paper • 2501.13007 • Published • 19 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 109 -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
Process Reinforcement through Implicit Rewards
Paper • 2502.01456 • Published • 62 -
One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
Paper • 2502.10454 • Published • 7 -
Large Language Models and Mathematical Reasoning Failures
Paper • 2502.11574 • Published • 3 -
PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
Paper • 2502.12054 • Published • 7 -
LightThinker: Thinking Step-by-Step Compression
Paper • 2502.15589 • Published • 31 -
OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
Paper • 2504.01943 • Published • 15 -
MolmoAct: Action Reasoning Models that can Reason in Space
Paper • 2508.07917 • Published • 44 -
StepWiser: Stepwise Generative Judges for Wiser Reasoning
Paper • 2508.19229 • Published • 20 -
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Paper • 2508.14029 • Published • 118 -
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Paper • 2602.08354 • Published • 259