相关论文: Outcome-based Exploration for LLM Reasoning

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

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 (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although…

In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particularly in understanding human intents, following user…

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal…

Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies with outcome supervision, tree search enables better…

While Large Language Models (LLMs) hold promise to become autonomous agents, they often explore suboptimally in sequential decision-making. Recent work has sought to enhance this capability via supervised fine-tuning (SFT) or reinforcement…

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal…

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

In this study, we present EventRL, a reinforcement learning approach developed to enhance event extraction for large language models (LLMs). EventRL utilizes outcome supervision with specific reward functions to tackle prevalent challenges…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during…

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with…

In this paper, a unified framework for exploration in reinforcement learning (RL) is proposed based on an option-critic model. The proposed framework learns to integrate a set of diverse exploration strategies so that the agent can…

Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an…

Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits…

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…