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.
arXiv:2605. 25143v2 Announce Type: replace Abstract: Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories.
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.
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...
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.
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.
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.
Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standard approaches such as independent sampling and sequential multi-turn refinement operate without token-level credit assignment, resulting in computational inefficiency, since valid reasoning prefixes are frequently discarded.
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.
TRACES (Tagging Reasoning Steps for Adaptive Cost‑Efficient Early‑Stopping) is a lightweight framework that tags reasoning steps of large‑language models in real time, enabling adaptive, cost‑efficient early stopping during inference. By monitoring the types of steps generated, the method identifies when models shift their reasoning after arriving at a correct answer, allowing for interpretable stopping criteria. Experiments on mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and knowledge benchmarks (MMLU, GPQA) show token reductions of 20–50% while preserving accuracy, with more conservative thresholds needed for harder tasks such as BeyondAIME and IMO AnswerBench.
arXiv:2510. 13940v4 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency.
arXiv:2602. 03203v2 Announce Type: replace-cross Abstract: Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces.
arXiv:2607. 01237v2 Announce Type: replace-cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput.