Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Paper
•
2501.18585
•
Published
•
61
Reasoning
-
-
Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization
Paper • 2412.18279 • Published -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Paper • 2501.19324 • Published • 39 -
Dynamic Scaling of Unit Tests for Code Reward Modeling
Paper • 2501.01054 • Published • 16 -
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Paper • 2411.04282 • Published • 37 -
SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights
Paper • 2410.09008 • Published • 17 -
Subtle Errors Matter: Preference Learning via Error-injected Self-editing
Paper • 2410.06638 • Published -
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Paper • 2502.04404 • Published • 25 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 58 -
SIFT: Grounding LLM Reasoning in Contexts via Stickers
Paper • 2502.14922 • Published • 32 -
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
Paper • 2404.13026 • Published • 24 -
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 61 -
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 36 -
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
Paper • 2503.12937 • Published • 30 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 119 -
T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models
Paper • 2504.04718 • Published • 42 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 43 -
Think on your Feet: Adaptive Thinking via Reinforcement Learning for Social Agents
Paper • 2505.02156 • Published • 18 -
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
Paper • 2504.20752 • Published • 92 -
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
Paper • 2505.07608 • Published • 82 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 188 -
Think Only When You Need with Large Hybrid-Reasoning Models
Paper • 2505.14631 • Published • 20 -
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
Paper • 2505.13215 • Published • 29 -
Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
Paper • 2505.19706 • Published • 3 -
rStar2-Agent: Agentic Reasoning Technical Report
Paper • 2508.20722 • Published • 117 -
Reverse-Engineered Reasoning for Open-Ended Generation
Paper • 2509.06160 • Published • 149