Related papers: LYNX: Learning Dynamic Exits for Confidence-Contro…

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…

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. However, these extended generations incur substantial memory footprint and computational overhead,…

To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the final answer. However, this couples reasoning to autoregressive generation and thereby…

Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we…

Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model. In this paper, we empirically analyze the working mechanism of…

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" process and the final response. A key factor influencing answer…

Recently, large language models (LLMs) have demonstrated outstanding reasoning capabilities on mathematical and coding tasks. However, their application to financial tasks-especially the most fundamental task of stock movement…

While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effectiveness in accurately adhering to instructions remains…

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Recent Large Reasoning Language Models (LRLMs) employ long chain-of-thought reasoning with complex reflection behaviors, typically signaled by specific trigger words (e.g., "Wait" and "Alternatively") to enhance performance. However, these…

Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across problems, inflating token usage and latency. This saturation of…

Reasoning models have demonstrated exceptional performance in tasks such as mathematics and logical reasoning, primarily due to their ability to engage in step-by-step thinking during the reasoning process. However, this often leads to…

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently…

Reasoning-oriented language models typically expose explicit reasoning as a long, front-loaded chain of "thinking" tokens before the main output, either always enabled or externally toggled at inference time. Although this can help on…

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process through counterfactual explanations, which identify the…

Prior work has shown that a significant driver of performance in reasoning models is their ability to reason and self-correct. A distinctive marker in these reasoning traces is the token wait, which often signals reasoning behavior such as…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…