Related papers: Z1: Efficient Test-time Scaling with Code

We propose integration of reasoning into speech large language models (speechLLMs) for the end-to-end slot-filling task. Inspired by the recent development of reasoning LLMs, we use a chain-of-thought framework to decompose the slot-filling…

Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-to-hard…

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting…

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…

Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning…

Large Reasoning Models (LRMs) achieve superior performance by extending the thought length. However, a lengthy thinking trajectory leads to reduced efficiency. Most of the existing methods are stuck in the assumption of overthinking and…

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

Temporal reasoning is pivotal for Large Language Models (LLMs) to comprehend the real world. However, existing works neglect the real-world challenges for temporal reasoning: (1) intensive temporal information, (2) fast-changing event…

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…

When faced with complex problems, we tend to engage in slower, more deliberate thinking. In contrast, for simple questions we give quick, intuitive responses. This dual-system thinking approach allows us to allocate cognitive resources…

Recent LLMs have significantly improved reasoning capabilities, primarily by including an explicit, lengthy Thinking process as part of generation. In this paper, we question whether this explicit thinking is necessary. Using the…

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…

In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a diverse spectrum of…

Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free…

Increasing test-time compute for LLMs shows promise across domains but remains underexplored in code generation, despite extensive study in math. In this paper, we propose S*, the first hybrid test-time scaling framework that substantially…

Large Reasoning Models (LRMs) often suffer from the ``over-thinking'' problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitigate this issue, such as length penalties or routing…

Reasoning-capable large language models (LLMs) achieve strong performance on complex tasks but often exhibit overthinking after distillation, generating unnecessarily long chain-of-thought (CoT) reasoning even for simple inputs and…

Eliciting explicit, step-by-step reasoning traces from large language models (LLMs) has emerged as a dominant paradigm for enhancing model capabilities. Although such reasoning strategies were originally designed for problems requiring…