相关论文: Replacing thinking with tool usage enables reasoni…

Leveraging inference-time search in large language models has proven effective in further enhancing a trained model's capability to solve complex mathematical and reasoning problems. However, this approach significantly increases…

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen…

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. To…

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity…

Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain-of-Thought (CoT)…

Large Language Models (LLMs) with reasoning capabilities have achieved state-of-the-art performance on a wide range of tasks. Despite its empirical success, the tasks and model scales at which reasoning becomes effective, as well as its…

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Large language models often require costly optimization, such as reinforcement learning, to master complex reasoning tasks. This work demonstrates that reasoning ability, once learned, can be extracted and transferred between models as a…

Chain-of-thought (CoT) rationale enables language models to use additional task-related text for problem-solving, benefiting not only from detailed reasoning steps but also from the expanded computational space of longer inputs. Prior work…

Reasoning capability plays a significantly critical role in the the broad applications of Large Language Models (LLMs). To enhance the reasoning performance of LLMs, diverse Reinforcement Learning (RL)-based fine-tuning approaches have been…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…

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…

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking…

Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether…