← Back to all news
arXiv Machine Learning By Niklas Muennighoff, Zhengyang Wang, Zeyi Chen, Weijia Shi, Binyuan Hui, John Yang, Dapeng Jiang, Mika Senghaas, Fares Obeid, Johannes Hagemann, Sami Jaghouar, Ludwig Schmidt, Percy Liang, Jason Wei, Andrew Y. Ng, Luke Zettlemoyer, Yejin Choi, Mike Lewis

Prefix Sliding for efficient test-time scaling

Read the original on arXiv Machine Learning →

The paper introduces Prefix Sliding, a method that discards intermediate reasoning tokens during test-time scaling of language models, keeping only the prefix with key instructions and the most recent few thousand tokens. This approach limits memory usage regardless of reasoning length, enabling efficient long-horizon scaling. Experiments show that without training, Prefix Sliding can triple inference speed while preserving performance, and with reinforcement learning it can further improve results on very long reasoning traces.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Sep 24

Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models

The paper introduces Causal Shortcut Learning (CSL), a framework that identifies token chains—called causal shortcuts—that guide Diffusion Language Models (DLMs) toward correct reasoning paths. By extracting these shortcuts and applying parallel prioritized masking during training, CSL improves both convergence speed and generation accuracy. Experiments on several reasoning benchmarks and two base models show CSL outperforms existing SFT-variant baselines, achieving an average 1.92% improvement over SFT-only models and up to 4.20% on MATH-500.

By Dian Jin, Kairong Han, Baohong Li, Xinpeng Dong, Zijing Hu, Nuanqiao Shan, Fei Wu, Kun Kuang
llmsdiffusionfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Aug 31

Sliding-window beats linear attention

arXiv:2608.28444v1 Announce Type: cross Abstract: Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previo...

By Alexia Jolicoeur-Martineau, Rhea Sanjay Sukthanker, Pashmina Cameron, Emy Gervais
llmsbenchmarks
More like this →
arXiv Machine Learning
Jul 24

Test-Time Scaling via Error Localization

arXiv:2607. 21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks.

By Rajiv Shailesh Chitale, Rahul Madhavan, Taneesh Gupta, Deepanway Ghosal, Aravindan Raghuveer
llmsbenchmarks
More like this →
arXiv AI
Aug 11

Thought-Level Beam Search for Reasoning

arXiv:2608. 08020v1 Announce Type: new Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it.

By Lijie Yang, Hongyin Luo, Tri Dao, Ravi Netravali
efficiencybenchmarks
More like this →
arXiv AI
Jun 15

Fractured Chain-of-Thought Reasoning

arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.

By Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong
llmsbenchmarks
More like this →