Related papers: DISPO: Enhancing Training Efficiency and Stability…

Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal…

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1,…

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging…

Reinforcement learning has been central to recent advances in large language model reasoning, but most algorithms rely on on-policy training that demands fresh rollouts at every update, limiting efficiency and scalability. Asynchronous RL…

Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…

Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance on multiple completions per prompt makes training computationally expensive. Although recent work has…

With the rapid development of deep learning, large language models have shown strong capabilities in complex reasoning tasks such as mathematical equation solving. However, their substantial computational and storage costs hinder practical…

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff''…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the reasoning capabilities of Large Language Models (LLMs). However, continuous training often leads to policy entropy collapse,…

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-quality data for training, which can stabilize RL training and…

DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings, they face limitations, including inconsistencies…

Asynchronous reinforcement learning has become increasingly central to scaling LLM post-training, delivering major throughput gains by decoupling rollout generation from policy updates. However, widely used policy-gradient objectives such…

Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the…

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods primarily rely on self-exploration or a single off-policy teacher…

Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Finetuning (RFT) methods is that they are on-policy RL in…

In neural combinatorial optimization (CO), reinforcement learning (RL) can turn a deep neural net into a fast, powerful heuristic solver of NP-hard problems. This approach has a great potential in practical applications because it allows…

As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM unlearning, which aims to remove the influence of specific…

As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning…