Related papers: Efficient LLM Reasoning via Variational Posterior …

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress…

Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify attention dispersion as the underlying cause: during…

While inference-time thinking allows Large Language Models (LLMs) to address complex problems, the extended thinking process can be unreliable or inconsistent because of the model's probabilistic nature, especially near its knowledge…

To enhance the reasoning capabilities of large language models (LLMs), self-consistency has become a popular approach, combining multiple samplings with majority voting. However, current methods are computationally expensive and…

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

Reinforcement learning-based retrieval-augmented generation (RAG) methods enhance the reasoning abilities of large language models (LLMs). However, most rely only on final-answer rewards, overlooking intermediate reasoning quality. This…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computation a task requires. We study budgeted inference-time reasoning for multiple tasks under a…

Large language models (LLMs) increasingly solve difficult problems by producing "reasoning traces" before emitting a final response. However, it remains unclear how accuracy and decision commitment evolve along a reasoning trajectory, and…

Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step…

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs significant…

Recent reasoning large language models (LLMs), such as OpenAI o1 and DeepSeek-R1, exhibit strong performance on complex tasks through test-time inference scaling. However, prior studies have shown that these models often incur significant…

Specialized reasoning language models (RLMs) have demonstrated that scaling test-time computation through detailed reasoning traces significantly enhances performance. Although these traces effectively facilitate knowledge distillation into…

Reasoning is increasingly crucial for various tasks. While chain-of-thought prompting enables large language models to leverage reasoning effectively, harnessing the reasoning capabilities of Vision-Language Models (VLMs) remains…

Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption,…

Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption and high inference latency. Existing reinforcement learning (RL) approaches for CoT…

Recent advances in deep learning have brought to the fore models that can make multiple computational steps in the service of completing a task; these are capable of describ- ing long-term dependencies in sequential data. Novel recurrent…