相关论文: Directional Reasoning Trajectory Change (DRTC): Id…

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Understanding uncertainty in chain-of-thought reasoning is critical for reliable deployment of large language models. In this work, we propose a simple yet effective diagnostic approach based on trajectory shape rather than scalar…

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…

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…

As chain-of-thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through…

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…

Central to many self-improvement pipelines for large language models (LLMs) is the assumption that models can improve by reflecting on past mistakes. We study a phenomenon termed contextual drag: the presence of failed attempts in the…

Process Reward Models (PRMs) have recently emerged as a powerful framework for supervising intermediate reasoning steps in large language models (LLMs). Previous PRMs are primarily trained on model final output responses and struggle to…

Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, the critical role of model uncertainty remains largely underexplored in…

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic…

Large Reasoning Models (LRMs) generate explicit reasoning traces alongside final answers, yet the extent to which these traces influence answer generation remains unclear. In this work, we conduct a three-stage investigation into the…

Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distillation, can be a cost-effective way to boost reasoning…

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Data drift is the change in model input data that is one of the key factors leading to machine learning models performance degradation over time. Monitoring drift helps detecting these issues and preventing their harmful consequences.…

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

As Large Language Models (LLMs) scale up and gain powerful Chain-of-Thoughts (CoTs) reasoning abilities, practical resource constraints drive efforts to distill these capabilities into more compact Smaller Language Models (SLMs). We find…

Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, largely due to the…

Enhancing the capability of large language models (LLMs) in reasoning has gained significant attention in recent years. Previous studies have demonstrated the effectiveness of various prompting strategies in aiding LLMs in reasoning (called…

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised…