Related papers: Selective Rollout: Mid-Trajectory Termination for …

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful framework for improving the reasoning abilities of Large Language Models (LLMs). However, current methods such as GRPO rely only on problems where the model responses to…

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…

Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets…

RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the…

Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Optimization (GRPO) serving as the dominant algorithm. We identify two overlooked…

Reinforcement learning improves LLM reasoning, yet sparse delayed reward over long sequences makes token-level credit assignment the key bottleneck. We study the verifiable-reward setting, where the final answer is checkable and multiple…

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all…

Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed…

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios,…

Unsupervised speech emotion recognition (SER) focuses on addressing the problem of data sparsity and annotation bias of emotional speech. Reinforcement learning (RL) is a promising method which enhances the performance through rule-based or…

Reinforcement Learning with Verifiable Rewards (RLVR), particularly GRPO, has become the standard for eliciting LLM reasoning. However, its efficiency in exploration and difficulty adaptation remains an open challenge. In this work, we…

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk…

Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, and long-horizon tasks remains challenging. While…

Reinforcement learning algorithms such as group-relative policy optimization (GRPO) have shown strong potential for improving the mathematical reasoning capabilities of large language models. While a growing body of work seeks to improve…

Automated Theorem Proving (ATP) represents a fundamental challenge in Artificial Intelligence (AI), requiring the construction of machine-verifiable proofs in formal languages such as Lean to evaluate AI reasoning capabilities.…

Aligning Large Language Models (LLMs) with human preferences typically relies on external supervision, which faces critical limitations: human annotations are scarce and subjective, reward models are vulnerable to reward hacking, and…

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…