Related papers: ReasonOps: Operator Segmentation for LLM Reasoning…

Large Language Models (LLMs) have transformed artificial intelligence from primarily generative systems into increasingly capable reasoning agents. Recent advances in theorem proving, autoformalization, symbolic reasoning, and…

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive…

Current Large Language Models (LLMs), especially Large Reasoning Models, can generate Chain-of-Thought (CoT) reasoning traces to illustrate how they produce final outputs, thereby facilitating trust calibration for users. However, these CoT…

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…

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 in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy…

Current comparisons of large reasoning models (LRMs) focus on macro-level statistics such as task accuracy or reasoning length. Whether different LRMs reason differently remains an open question. To address this gap, we introduce the…

Large reasoning models (LRMs) have garnered significant attention from researchers owing to their exceptional capability in addressing complex tasks. Motivated by the observed human-like behaviors in their reasoning processes, this paper…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the question of what…

Reasoning-capable large language models solve hard problems by emitting long chains of thought, paying heavily in latency, GPU time, and energy. Casual inspection of their traces reveals extensive reformulation, verification, and circular…

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…

Currently, many large language models (LLMs) are utilized for software engineering tasks such as code generation. The emergence of more advanced models known as large reasoning models (LRMs), such as OpenAI's o3, DeepSeek R1, and Qwen3.…

Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But how robust are these reasoning traces to disruptions that…

Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset…

Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reasoning structure helps, and when it instead reduces efficiency…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution…

Current frontier large-language models rely on reasoning to achieve state-of-the-art performance. Many existing interpretability are limited in this area, as standard methods have been designed to study single forward passes of a model…

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable…