Related papers: SmartThinker: Learning to Compress and Preserve Re…

Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs…

Large reasoning models have demonstrated remarkable performance on complex reasoning tasks, yet the excessive length of their chain-of-thought outputs remains a major practical bottleneck due to high computation cost and poor deployability.…

Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long…

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…

Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the \textit{reasoning} or \textit{thinking} capabilities of LLMs…

Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long reasoning chains. While current solutions improve token efficiency, they often sacrifice…

Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent reasoning benefit…

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcement learning (RL)-based solutions tackle this problem by…

The recent rise of Large Reasoning Models (LRMs) has significantly improved multi-step reasoning performance, but often at the cost of generating excessively long reasoning chains. This paper revisits the efficiency of such reasoning…

Recent studies generally enhance MLLMs' reasoning capabilities via supervised fine-tuning on high-quality chain-of-thought reasoning data, which often leads models to merely imitate successful reasoning paths without understanding what the…

Recent advances in large reasoning models have been driven by reinforcement learning and test-time scaling, accompanied by growing interest in latent rather than purely textual reasoning. However, existing latent reasoning methods lack…

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths…

Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the ``think-then-answer'' paradigm, which enhances both accuracy and interpretability. However, current LRMs exhibit two critical…

Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or redundant reasoning -- so-called overthinking -- can increase…

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape…

Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a substantial increase in reasoning budget. Recent studies…

We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, ThinkTwice first…