RL + Transformer = A General-Purpose Problem Solver
Paper
•
2501.14176
•
Published
•
25
RL+reason model
-
-
Towards General-Purpose Model-Free Reinforcement Learning
Paper • 2501.16142 • Published • 26 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 108 -
MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
Paper • 2412.12098 • Published • 4 -
RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
Paper • 2412.09858 • Published • 1 -
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Paper • 2501.18585 • Published • 56 -
o3-mini vs DeepSeek-R1: Which One is Safer?
Paper • 2501.18438 • Published • 22 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 108 -
Process Reinforcement through Implicit Rewards
Paper • 2502.01456 • Published • 55 -
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Paper • 2502.01081 • Published • 14 -
Improving Transformer World Models for Data-Efficient RL
Paper • 2502.01591 • Published • 9 -
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
Paper • 2502.02508 • Published • 23 -
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 55 -
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking
Paper • 2502.02339 • Published • 22 -
A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Paper • 2502.01618 • Published • 10 -
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
Paper • 2502.03860 • Published • 24 -
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Paper • 2502.04404 • Published • 23 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 141 -
ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
Paper • 2502.06772 • Published • 20 -
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Paper • 2502.07374 • Published • 36 -
Teaching Language Models to Critique via Reinforcement Learning
Paper • 2502.03492 • Published • 24 -
An Open Recipe: Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging
Paper • 2502.09056 • Published • 30 -
Logical Reasoning in Large Language Models: A Survey
Paper • 2502.09100 • Published • 22 -
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
Paper • 2502.08235 • Published • 54 -
video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
Paper • 2502.11775 • Published • 8 -
Soundwave: Less is More for Speech-Text Alignment in LLMs
Paper • 2502.12900 • Published • 76 -
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Paper • 2502.12215 • Published • 16 -
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 28 -
Thinking Preference Optimization
Paper • 2502.13173 • Published • 17 -
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Paper • 2502.14768 • Published • 44 -
LightThinker: Thinking Step-by-Step Compression
Paper • 2502.15589 • Published • 26 -
The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer
Paper • 2502.15631 • Published • 8 -
Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models
Paper • 2502.16033 • Published • 15 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 64 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 74 -
MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
Paper • 2502.19634 • Published • 56 -
FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
Paper • 2502.20238 • Published • 23 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 55 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 18 -
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Paper • 2503.01307 • Published • 24 -
Efficient Test-Time Scaling via Self-Calibration
Paper • 2503.00031 • Published • 11 -
LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
Paper • 2503.00735 • Published • 14