5 papers
Message Passing Enables Efficient Reasoning
Xuecheng Liu, Daman Arora, Gokul Swamy +1
While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is a computational bottleneck.…
Expanding the Capabilities of Reinforcement Learning via Text Feedback
Yuda Song, Lili Chen, Fahim Tajwar +5
The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other…
Maximum Likelihood Reinforcement Learning
Fahim Tajwar, Guanning Zeng, Yueer Zhou +7
Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation…
Training Language Models to Reason Efficiently
Daman Arora, Andrea Zanette
Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alt…
Can Large Reasoning Models Self-Train?
Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov +2
Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own ju…