Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show that this algorithmic separation is not fundamental. By deriving suitable RL objectives as maximum-likelihood fitting to...
Yu-Da Song, Alvin Zhang, Fahim Tajwar et al.· 0 citations
It is shown that a small, open model can be trained via reinforcement learning to perform the same functionality as commercial LLMs, and on ToolBench, a Qwen3-8B model post-trained with the recipe outperforms Llama-4-Maverick (402B).
Zhao-Yi Zhou, Akshayaa Magesh, Jeongyeol Kwon et al.· 1 citation
This work proposes training models to fail gracefully: to preserve successful behavior whenever possible while learning to execute a safe fallback policy when acting would be unreliable, and shows that reinforcement learning can not only incentivize models to succeed, but also to reason about the limits of their capabi...
Daman Arora, Xue-Chen Liu, H. Singh et al.· 0 citations
Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textual chain-of-thought reasoning can partially mitigate this issue by encouraging models to decompose visual questions into intermediate evidence-seeking steps, b...
message Passing Language Models, a framework for LLM reasoning in which threads communicate directly via lightweight send and receive primitives, and shows that appropriately prompted large pre-trained models follow the MPLM protocol, achieving competitive results on long-context question answering relative to popular...
Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their discoveries in prose, which may not provide a compact, explicit account of how the environment works. Inspired by how scientists organize observations into testable, pre...
Guan-Ning Zeng, Jia-Ni Wang, Wenjie Ma et al.· arXiv.org· 0 citations
This work introduces harness learning, which trains a proposer model to revise a solver's harness using execution feedback, and formulate this process as meta-learning over executable programs, with harness revisions playing the role of weight updates in gradient-based adaptation.
Alvin Zhang, Xue-Chen Liu, Zi-Xuan Wang et al.· arXiv.org· 0 citations
Tail-Likelihood Reinforcement Learning (TailRL), which maximizes the log-probability of exceeding a randomly chosen reward threshold, which gives more weight to rare, high-reward rollouts and can be interpreted as a mixture of Best-of-k gradients.
Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.