Related papers: Stabilizing MoE Reinforcement Learning by Aligning…

In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which…

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedback. However, large-scale preference datasets, whether collected from crowdsourced…

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Mixture-of-Experts (MoE) models achieve efficient scaling through sparse expert activation, but often suffer from suboptimal routing decisions due to distribution shifts in deployment. While existing test-time adaptation methods could…

The rapid emergence of diverse large language models (LLMs) has spurred the development of LLM routers that assign user queries to the most suitable model. However, existing LLM routers typically perform a single-round, one-to-one mapping…

The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE…

Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable degenerate optimization behaviors under standard full-parameter fine-tuning. In our…

In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems. When learning a dynamical system, one needs to stabilize the unknown dynamics in order to avoid system blow-ups. We propose an…

Traditional Reinforcement Learning (RL) frameworks generally assume that the agent perceives the state of the underlying Markov process instantaneously and then takes actions accordingly. If the agent cannot directly observe the process,…

Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there…

The generation quality of large language models (LLMs) is often improved by utilizing inference-time sequence-level scaling methods (e.g., Chain-of-Thought). We introduce hyper-parallel scaling, a complementary framework that improves…

Mixture-of-Experts (MoE) architectures have become the key to scaling modern LLMs, yet little is understood about how their sparse routing dynamics respond to multilingual data. In this work, we analyze expert routing patterns using…

Reinforcement learning (RL) has been widely applied to dynamic routing, modulation and spectrum assignment (RMSA) in optical networks, yet no prior work has trained a transformer model for this task. We attribute this to the high data and…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language models. As models extend to omni-modal inputs and agentic multi-turn workflows, RL training…

Despite recent advancements in offline multi-task reinforcement learning (MTRL) have harnessed the powerful capabilities of the Transformer architecture, most approaches focus on a limited number of tasks, with scaling to extremely massive…

We study the inverse reinforcement learning (IRL) problem under a transition dynamics mismatch between the expert and the learner. Specifically, we consider the Maximum Causal Entropy (MCE) IRL learner model and provide a tight upper bound…

Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel…

We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this size exposes critical inefficiencies-zero-variance prompts…