Related papers: Atomic Skills are the Prerequisite: When Reinforce…

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it…

Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Existing work trains exclusively on a single benchmark, leaving open how the composition of…

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remains unclear. We revisit the common claim that ``SFT memorizes,…

Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to…

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains a…

Medical imaging has revolutionized diagnosis, yet unnecessary procedures are rising, exposing patients to radiation and stress, limiting equitable access, and straining healthcare systems. The American College of Radiology Appropriateness…

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In…

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

In this work, motivated by recent manufacturing trends, we investigate autonomous robotic assembly. Industrial assembly tasks require contact-rich manipulation skills, which are challenging to acquire using classical control and motion…

Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through…

Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs…

Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two-stage curriculum that first elicits reasoning skills in…

The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions. Further progress hinges on combining RL with modern function approximators such as kernel functions and deep neural…

Deep reinforcement learning (RL) is a promising approach to solving complex robotics problems. However, the process of learning through trial-and-error interactions is often highly time-consuming, despite recent advancements in RL…

Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding errors under…

Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents…