Related papers: WIST: Web-Grounded Iterative Self-Play Tree for Do…

Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent works have begun exploring how to train LLMs to use search engines more effectively as tools for…

Personalized text generation requires a unique ability of large language models (LLMs) to learn from context that they often do not encounter during their standard training. One way to encourage LLMs to better use personalized context for…

Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is…

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but…

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in…

Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a…

Progress in many task domains emerges from repeated revisions to previous solution attempts. Training agents that can reliably self-improve over such sequences at inference-time is a natural target for reinforcement learning (RL), yet the…

We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model with full reference solutions as context, enabling fine-grained…

In statistical modelling the biggest threat is concept drift which makes the model gradually showing deteriorating performance over time. There are state of the art methodologies to detect the impact of concept drift, however general…

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…

Inspired by recent findings on the fractal geometry of language, we introduce Recursive INference Scaling (RINS) as a complementary, plug-in recipe for scaling inference time in language and multimodal systems. RINS is a particular form of…

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales…

A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more computation or interaction is available. Even the…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on…

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge in ICRL is reward estimation, as models typically lack…

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains…

Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to…

Reinforcement post training (RPT) has recently shown promise in improving the reasoning abilities of large language models (LLMs). However, it remains unclear how well these improvements generalize to new domains, as prior work evaluates…