Aug 2026· 1 citation· ⚡ 1 influential· 132 references
Computer Science
TL;DR
Prefix Sliding is proposed, which discards tokens during reasoning that are not part of the prefix or the window of the last few thousand tokens, allowing for efficient long-horizon test-time scaling.
Abstract
Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer when solving a problem. As models keep the entire reasoning trace in memory via full attention, hard tasks that need long thinking can be prohibitively expensive. However, we find most intermediate reasoning tokens lose importance as the model continues reasoning. This calls into question whether retaining them is worth the cost. Based on this insight, we propose Prefix Sliding, which discards tokens during reasoning that are not part of the prefix or the window of the last few thousand tokens. The prefix has key instructions and tools available to the model, while the most recent tokens are the current reasoning the model is working on. This caps the total memory requirement regardless of how long the model reasons, allowing for efficient long-horizon test-time scaling. Without training, Prefix Sliding can make existing models 3x faster while maintaining performance. Training with Prefix Sliding using reinforcement learning can achieve better performance by enabling scaling to reasoning traces beyond a hundred thousand tokens. Ablations show Prefix Sliding outperforms summarizing intermediate tokens or vanilla sliding window. Our code is at https://github.com/Muennighoff/prefix-sliding
This work introduces Test-Time Scaling via Error Localization (TTEL), an inference-time algorithm that utilizes fixed or environment feedback to perform token-level error localization and establishes strictly dominating Pareto frontiers across sequential reasoning domains.
By periodically pruning unpromising trajectories and immediately branching from high-quality prefixes, Gambit dynamically concentrates compute onto the most promising reasoning traces via a light-weight scorer probing hidden states while maintaining continuous high hardware utilization.
Lijie Yang, Hongyin Luo, Tri Dao et al.· 0 citations
The first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing is conducted - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation.
Davide Romano, Kanak Raj, Jerrod Parker et al.· 0 citations
Under the standard approximation of taking gradients at the chunk-start weights, a closed-form state transition is derived that exactly reproduces the chunk-end fast-weight and momentum states of the per-token recurrence of Test-Time Training.
Zeyun Zhong, Joya Chen, Manuel Martín et al.· 1 citation
Large Language Models (LLMs) trained using Chain-of-Thought (CoT) supervision have achieved state-of-the-art performance on complex reasoning tasks. However, the generation of long reasoning chains introduces substantial computational overhead during inference, limiting their deployment in low-latency and resource-constrained environments. This paper proposes AdaptiReason, a novel framework that dynamically compresses intermediate reasoning steps based on task difficulty and model confidence without requiring retraining of the underlying base model. AdaptiReason employs a lightweight difficulty estimator to determine the appropriate reasoning depth for each input, followed by a learned token-pruning policy that eliminates redundant or low-information reasoning steps. Experimental evaluation on the MATH, GSM8K, and ARC-Challenge benchmarks demonstrates that AdaptiReason reduces the average number of generated tokens by 3.7× while preserving 98.2% of the baseline reasoning accuracy. Furthermore, the proposed framework is model-agnostic and can be seamlessly integrated with instruction-tuned LLMs without requiring access to model parameters, relying solely on output logits for adaptive reasoning compression. The results demonstrate that AdaptiReason significantly improves inference efficiency while maintaining high reasoning performance, making it suitable for real-time and resource-constrained LLM applications.
V. A, Mithaguru, Amrita Kundu et al.· 2026 4th International Confe...· 0 citations
An exam-style evaluation framework is introduced for studying the global budget allocation of reasoning language models when multiple problems share an end-to-end cost or latency constraint, in which a model must distribute one shared token budget across questions with different difficulty and point values.
Chenrui Fan, Yize Cheng, Ming Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
