Related papers: Alleviating Sparse Rewards by Modeling Step-Wise a…

Training tool-calling agents with reinforcement learning on multi-turn tasks remains challenging due to sparse outcome rewards and difficult credit assignment across conversation turns. We present the first application of MT-GRPO…

Recent Large Reasoning Models (LRMs) have achieved remarkable performance in solving complex problems via supervised fine-tuning (SFT) and reinforcement learning (RL). Although existing RL algorithms significantly enhance model accuracy,…

Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates. We identify…

Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewards. These obscure which tokens actually contribute to…

Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models. We adapt the Group Relative…

Generative Retrieval (GR) offers a promising paradigm for recommendation through next-token prediction (NTP). However, scaling it to large-scale industrial systems introduces three challenges: (i) within a single request, the identical…

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days…

Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital…

Group Relative Policy Optimization (GRPO) performs coarse-grained credit assignment in reinforcement learning with verifiable rewards (RLVR) by assigning the same advantage to all tokens in a rollout. Process reward models can provide…

Group Relative Policy Optimization (GRPO) has been shown to be an effective algorithm when an accurate reward model is available. However, such a highly reliable reward model is not available in many real-world tasks. In this paper, we…

Proximal Policy Optimization (PPO)-based reinforcement learning from human feedback (RLHF) is a widely adopted paradigm for aligning large language models (LLMs) with human preferences. However, its training pipeline suffers from…

Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based…

Large reasoning models trained with reinforcement learning and verifiable rewards (RLVR) achieve strong performance on complex reasoning tasks, yet often overthink, generating redundant reasoning without performance gains. Existing…

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for…

Reinforcement learning (RL) holds significant promise for training LLM agents to handle complex, goal-oriented tasks that require multi-step interactions with external environments. However, a critical challenge when applying RL to these…

Designing dense rewards is crucial for reinforcement learning (RL), yet in robotics it often demands extensive manual effort and lacks scalability. One promising solution is to view task progress as a dense reward signal, as it quantifies…

Reinforcement learning algorithms often suffer from slow convergence due to sparse reward signals, particularly in complex environments where feedback is delayed or infrequent. This paper introduces the Psychological Regret Model (PRM), a…

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…