# Z1: Efficient Test-time Scaling with Code

arXiv: https://arxiv.org/abs/2504.00810 · HTML: https://mlsanity.com/paper/2504.00810/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 23 of 23)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [SWE-Lancer: Can Frontier LLMs Earn 1 Million from Real-World Freelance Software Engineering?](https://mlsanity.com/paper/2502.12115/) (2025)
- [WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning](https://mlsanity.com/paper/2312.14187/) (2023)

## Built on by (most cited first, 30 of 35)

- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning](https://mlsanity.com/paper/2505.17813/) (2025)
- [Steering LLM Thinking with Budget Guidance](https://mlsanity.com/paper/2506.13752/) (2025)
- [Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs](https://mlsanity.com/paper/2507.02076/) (2025)
- [MUR: Momentum Uncertainty guided Reasoning for Large Language Models](https://mlsanity.com/paper/2507.14958/) (2025)
- [Generative AI Act II: Test Time Scaling Drives Cognition Engineering](https://mlsanity.com/paper/2504.13828/) (2025)
- [AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models](https://mlsanity.com/paper/2505.22662/) (2025)
- [Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models](https://mlsanity.com/paper/2505.21765/) (2025)
- [Exploring the System 1 Thinking Capability of Large Reasoning Models](https://mlsanity.com/paper/2504.10368/) (2025)
- [Shadow-FT: Tuning Instruct Model via Training on Paired Base Model](https://mlsanity.com/paper/2505.12716/) (2025)
- [Revisiting Model Interpolation for Efficient Reasoning](https://mlsanity.com/paper/2510.10977/) (2025)
- [Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning](https://mlsanity.com/paper/2506.04611/) (2025)
- [ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving](https://mlsanity.com/paper/2505.12717/) (2025)
- [SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning](https://mlsanity.com/paper/2505.16368/) (2025)
- [How Far Are We from Optimal Reasoning Efficiency?](https://mlsanity.com/paper/2506.07104/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners](https://mlsanity.com/paper/2505.16322/) (2025)
- [AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up](https://mlsanity.com/paper/2505.24584/) (2025)
- [J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge](https://mlsanity.com/paper/2505.11875/) (2025)
- [DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models](https://mlsanity.com/paper/2511.01170/) (2025)
- [Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models](https://mlsanity.com/paper/2508.03363/) (2025)
- [Understanding the Role of Training Data in Test-Time Scaling](https://mlsanity.com/paper/2510.03605/) (2025)
- [How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective](https://mlsanity.com/paper/2510.08720/) (2025)
- [Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience](https://mlsanity.com/paper/2505.05515/) (2025)
- [R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning](https://mlsanity.com/paper/2604.03004/) (2026)
- [Efficient Test-Time Scaling via Temporal Reasoning Aggregation](https://mlsanity.com/paper/2604.17304/) (2026)
- [Fast, Slow, and Tool-augmented Thinking for LLMs: A Review](https://mlsanity.com/paper/2508.12265/) (2025)
- [Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search](https://mlsanity.com/paper/2509.25420/) (2025)
- [RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning](https://mlsanity.com/paper/2604.00790/) (2026)

## Abstract (arXiv)

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.