Related papers: RESTRAIN: From Spurious Votes to Signals -- Self-D…

Reinforcement learning with verifiable rewards (RLVR) scales the reasoning ability of large language models (LLMs) but remains bottlenecked by limited labeled samples for continued data scaling. Reinforcement learning with intrinsic rewards…

Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals…

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to…

Reinforcement learning with verifiable rewards (RLVR) enhances the reasoning of large language models (LLMs), but standard RLVR often depends on human-annotated answers or carefully curated reward specifications. In machine-checkable…

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimization, which, however, suffers from high annotation costs.…

While reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs), its reliance on human-annotated labels leads to the scaling up dilemma, especially for complex tasks.…

Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard to use in open-ended domains where correctness is ambiguous and cannot be verified.…

Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) for improving…

Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority…

Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…

Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised…

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium…

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior works have made significant progress in applying the Test-Time…

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected data. However, it faces challenges of distributional shift, where the learned policy may encounter unseen scenarios not covered in the offline data.…

Recent advances in large language models have demonstrated the promise of unsupervised reinforcement learning (RL) methods for enhancing reasoning capabilities without external supervision. However, the generalizability of these label-free…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…

Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent…

Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU learning is to sample a set of pseudo-negatives from the…