Related papers: Tool Verification for Test-Time Reinforcement Lear…
Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, particularly in…
Groundbreaking successes have been achieved by Deep Reinforcement Learning (DRL) in solving practical decision-making problems. Robotics, in particular, can involve high-cost hardware and human interactions. Hence, scrupulous evaluations of…
The successes of reinforcement learning in recent years are underpinned by the characterization of suitable reward functions. However, in settings where such rewards are non-intuitive, difficult to define, or otherwise error-prone in their…
Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…
Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…
Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such…
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these…
Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limited: intermediate…
Code verifiers play a critical role in post-verification for LLM-based code generation, yet existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency. While reinforcement learning…
Learning to adapt pretrained language models to unlabeled, out-of-distribution data is a critical challenge, as models often falter on structurally novel reasoning tasks even while excelling within their training distribution. We introduce…
In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems, where the aim is…
Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…
Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…
Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on…
The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model's context window limit, the entire context cannot be…
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in multiple domains, yet outcome-only scalar rewards are often sparse and uninformative, especially on failed samples, where they merely indicate…
Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…
Trustworthy verifiers are essential for the success of reinforcement learning with verifiable reward (RLVR), which is the core methodology behind various large reasoning models such as DeepSeek-R1. In complex domains like mathematical…
We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms by means of a control strategy with limited knowledge of the system model. By tutoring the learning process, the…
Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…