Z1: Efficient Test-time Scaling with Code

• URL: http://arxiv.org/abs/2504.00810v1
• Date: Tue, 01 Apr 2025 14:01:50 GMT
• Title: Z1: Efficient Test-time Scaling with Code
• Authors: Zhaojian Yu, Yinghao Wu, Yilun Zhao, Arman Cohan, Xiao-Ping Zhang,
• Abstract summary: Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling.<n>We propose an efficient test-time scaling method that trains LLMs on code-related reasoning trajectories.<n>We present a novel Shifted Thinking Window to mitigate overthinking overhead.
• Score: 26.374317704720234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token costs. In this paper, we propose an efficient test-time scaling method that trains LLMs on code-related reasoning trajectories, facilitating their reduction of excess thinking tokens while maintaining performance. First, we create Z1-Code-Reasoning-107K, a curated dataset of simple and complex coding problems paired with their short and long solution trajectories. Second, we present a novel Shifted Thinking Window to mitigate overthinking overhead by removing context-delimiting tags (e.g., <think>. . . </think>) and capping reasoning tokens. Trained with long and short trajectory data and equipped with Shifted Thinking Window, our model, Z1-7B, demonstrates the ability to adjust its reasoning level as the complexity of problems and exhibits efficient test-time scaling across different reasoning tasks that matches R1-Distill-Qwen-7B performance with about 30% of its average thinking tokens. Notably, fine-tuned with only code trajectories, Z1-7B demonstrates generalization to broader reasoning tasks (47.5% on GPQA Diamond). Our analysis of efficient reasoning elicitation also provides valuable insights for future research.

Related papers

• Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching [60.04718679054704]
  We introduce Sketch-of-Thought (SoT), a novel prompting framework.<n>It combines cognitive-inspired reasoning paradigms with linguistic constraints to minimize token usage.<n>SoT achieves token reductions of 76% with negligible accuracy impact.
  arXiv  Detail & Related papers  (2025-03-07T06:57:17Z)
• DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models [31.189242663680695]
  This paper introduces Difficulty-Adaptive Slow-Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought(CoT) based on problem difficulty.<n>Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking while preserving reasoning accuracy on complex problems.
  arXiv  Detail & Related papers  (2025-03-06T14:23:06Z)
• How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach [4.055489363682199]
  We conduct the first systematic study of the relationship between reasoning length and model performance. We show that this tradeoff persists across even very distinct reasoning chains. We show that prompt-based compression strategies operate far from theoretical limits.
  arXiv  Detail & Related papers  (2025-03-03T03:48:20Z)
• Chain of Draft: Thinking Faster by Writing Less [37.492654173517046]
  Chain of Draft (CoD) is a novel paradigm inspired by human cognitive processes.<n>CoD generates minimalistic yet informative intermediate reasoning outputs while solving tasks.
  arXiv  Detail & Related papers  (2025-02-25T19:36:06Z)
• LightThinker: Thinking Step-by-Step Compression [53.8069487638972]
  We propose LightThinker, a method that enables large language models to dynamically compress intermediate thoughts during reasoning. Inspired by human cognitive processes, LightThinker compresses thought steps into compact representations and discards the original reasoning chains. Experiments show that LightThinker reduces peak memory usage and inference time, while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-02-21T16:57:22Z)
• Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs [86.79757571440082]
  Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks. We identify a phenomenon we term underthinking, where o1-like LLMs frequently switch between different reasoning thoughts. We propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts.
  arXiv  Detail & Related papers  (2025-01-30T18:58:18Z)
• O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning [98.3430004984531]
  We propose Length-Harmonizing Fine-Tuning (O1-Pruner) to minimize reasoning overhead while maintaining accuracy.<n>Our code is coming soon at https://github.com/StarDewXXX/O1-Pruner.
  arXiv  Detail & Related papers  (2025-01-22T01:35:11Z)
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
  o1-like models can emulate human-like long-time thinking during inference.<n>This paper presents the first comprehensive study on the prevalent issue of overthinking in these models.<n>We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
  arXiv  Detail & Related papers  (2024-12-30T18:55:12Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [53.51560766150442]
  Critical tokens are elements within reasoning trajectories that significantly influence incorrect outcomes. We present a novel framework for identifying these tokens through rollout sampling. We show that identifying and replacing critical tokens significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs [9.561022942046279]
  We propose Divide and Conquer Reasoning (DCR) to enhance the reasoning capability of large language models (LLMs) We first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers. In particular, we first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers.
  arXiv  Detail & Related papers  (2024-01-10T14:38:46Z)
• Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning [16.495754104540605]
  Large language models (LLMs) can generate code-like plans for complex inference tasks such as visual reasoning. We propose a hierarchical plan-searching algorithm that integrates the one-stop reasoning (fast) and the Tree-of-thought (slow)
  arXiv  Detail & Related papers  (2023-08-18T16:21:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.