RL + Transformer = A General-Purpose Problem Solver
Paper
•
2501.14176
•
Published
•
22
RL+reason model
-
-
Towards General-Purpose Model-Free Reinforcement Learning
Paper • 2501.16142 • Published • 24 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 100 -
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 • 51 -
o3-mini vs DeepSeek-R1: Which One is Safer?
Paper • 2501.18438 • Published • 21 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 88 -
Process Reinforcement through Implicit Rewards
Paper • 2502.01456 • Published • 53 -
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Paper • 2502.01081 • Published • 9 -
Improving Transformer World Models for Data-Efficient RL
Paper • 2502.01591 • Published • 8 -
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
Paper • 2502.02508 • Published • 16 -
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 32 -
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking
Paper • 2502.02339 • Published • 13 -
A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Paper • 2502.01618 • Published • 5