Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling

• URL: http://arxiv.org/abs/2509.19645v1
• Date: Tue, 23 Sep 2025 23:52:07 GMT
• Title: Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling
• Abstract summary: Test-time scaling (TTS) has emerged as a promising direction to exploit the hidden reasoning capabilities of large language models (LLMs)<n>We propose a system-driven perspective on TTS, analyzing how reasoning models scale against practical metrics, such as latency and cost-per-token.
• Score: 8.855653249643089
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time scaling (TTS) has recently emerged as a promising direction to exploit the hidden reasoning capabilities of pre-trained large language models (LLMs). However, existing scaling methods narrowly focus on the compute-optimal Pareto-frontier, ignoring the simple fact that compute-optimal is not always system-optimal. In this work, we propose a system-driven perspective on TTS, analyzing how reasoning models scale against practical metrics, such as latency and cost-per-token. By evaluating the impact of popular optimizations such as tensor parallelism and speculative decoding, our preliminary analysis reveals the limitations of current methods and calls for a paradigm shift toward holistic, system-aware evaluations that capture the true essence of scaling laws at inference time.

Related papers

• When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models [92.71325249013535]
  Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inference-time compute to a fixed model prior.<n>This survey systematizes recent progress in tree-search-based reasoning, viewing inference as instance-specific optimization rather than decoding.
  arXiv  Detail & Related papers  (2026-08-31T07:49:56Z)
• ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning [110.46431027868954]
  ThinkBooster is a framework for seamless test-time compute scaling of large language model (LLM) reasoning.<n>It consists of a modular Python library implementing state-of-the-art TTC scaling strategy and scorer families.<n>A deployable OpenAI-compatible proxy service enables drop-in integration of adaptive reasoning into real-world applications.
  arXiv  Detail & Related papers  (2026-06-05T05:28:46Z)
• Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training [7.267441247692648]
  We propose a novel framework to establish relationships between compute budget and optimal hyperparameters for a given checkpoint.<n>We show that our method reduces the hyperparameter search overhead by up to 90% while achieving comparable or superior performance relative to baselines.<n>This model-agnostic framework generalizes across architectures, providing a principled and efficient methodology for diverse continued pre-training scenarios.
  arXiv  Detail & Related papers  (2026-06-04T02:32:11Z)
• Deriving Hyperparameter Scaling Laws via Modern Optimization Theory [55.63126290312615]
  We study modern first-order boundss for methods based on the Linear Minimization Oracle (LMO)<n>Treating bounds in recent literature as a proxy and minimizing them across different tuning regimes yields closed-form power-law schedules for learning rate, momentum, and batch size.<n>Our results draw particular attention to the interaction between momentum and batch-size scaling, suggesting that optimal performance may be achieved with several scaling strategies.
  arXiv  Detail & Related papers  (2026-03-16T22:21:27Z)
• Beyond the Ideal: Analyzing the Inexact Muon Update [54.70108543057578]
  We show first analysis of the inexactized update at Muon's core.<n>We reveal a fundamental coupling between this inexactness and the optimal step size and momentum.
  arXiv  Detail & Related papers  (2025-10-22T18:01:07Z)
• ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models [102.4511331368587]
  ARISE (Adaptive Resolution-aware Scaling Evaluation) is a novel metric designed to assess the test-time scaling effectiveness of large reasoning models.<n>We conduct comprehensive experiments evaluating state-of-the-art reasoning models across diverse domains.
  arXiv  Detail & Related papers  (2025-10-07T15:10:51Z)
• Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling [38.27469349005585]
  Test-time scaling is a powerful paradigm for enhancing the reasoning capabilities of large language models.<n>Test-time scaling is inherently inefficient due to the generation of redundant and repetitive reasoning traces.<n>We introduce the first comprehensive benchmark designed to evaluate speculative decoding methods for accelerating test-time scaling.
  arXiv  Detail & Related papers  (2025-08-30T01:54:55Z)
• SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression [15.87106741558898]
  Post-training methods incur substantial computational overhead due to auxiliary models and overthinking.<n>We propose Self-traced Step-wise Preference Optimization (SSPO), a plug RLgable process supervision framework.<n>SSPO uses step-wise preference signals generated by the model itself to guide the optimization process for reasoning compression.
  arXiv  Detail & Related papers  (2025-08-18T04:02:15Z)
• Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models [58.36334504216682]
  Test-Time Scaling is a promising approach to progressively elicit the model's intelligence during inference.<n>In this paper, we focus on training-free TTS methods for reasoning.<n>We introduce a novel inference paradigm called Hybrid Test-Time Scaling.
  arXiv  Detail & Related papers  (2025-07-21T11:28:09Z)
• Probabilistic Optimality for Inference-time Scaling [8.126757296203957]
  Inference-time scaling has emerged as a powerful technique for enhancing the reasoning performance of Large Language Models (LLMs)<n>We propose a probabilistic framework that formalizes the optimality of inference-time scaling under the assumption that parallel samples are independently and identically distributed.<n>We develop OptScale, a practical algorithm that dynamically determines the optimal number of sampled responses.
  arXiv  Detail & Related papers  (2025-06-27T16:44:11Z)
• Kinetics: Rethinking Test-Time Scaling Laws [18.325591438335007]
  Kinetics Scaling Law suggests that test-time compute is more effective when used on models above a threshold than smaller ones.<n>Motivated by this, we propose a new scaling paradigm centered on sparse attention, which lowers per-token cost and enables longer generations and more parallel samples.
  arXiv  Detail & Related papers  (2025-06-05T17:59:24Z)
• Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks [100.13335639780415]
  Scaling laws often follow the power-law and proposed several variants of power-law functions to predict the scaling behavior at larger scales.<n>Existing methods mostly rely on point estimation and do not quantify uncertainty, which is crucial for real-world applications.<n>In this work, we explore a Bayesian framework based on Prior-data Fitted Networks (PFNs) for neural scaling law extrapolation.
  arXiv  Detail & Related papers  (2025-05-29T03:19:17Z)
• Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models [7.2703757624760526]
  Large reasoning models (LRMs) have exhibited the capacity of enhancing reasoning performance via internal test-time scaling.<n>As we push these scaling boundaries, understanding the practical limits and achieving optimal resource allocation becomes a critical challenge.<n>In this paper, we investigate the scaling plateau of test-time scaling and introduce the Test-Time Scaling Performance Model (TTSPM)
  arXiv  Detail & Related papers  (2025-05-26T20:58:45Z)
• Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory [79.63672515243765]
  In this paper, we focus on a standard and realistic scaling setting: majority voting.<n>We show that as the sampling time and computational overhead increase, complicated prompting strategies with superior initial performance gradually fall behind simple Chain-of-Thought.<n>We propose a probabilistic method to efficiently predict scaling performance and identify the best prompting strategy under large sampling times.
  arXiv  Detail & Related papers  (2025-05-16T08:28:57Z)
• Scaling Laws Beyond Backpropagation [64.0476282000118]
  We study the ability of Direct Feedback Alignment to train causal decoder-only Transformers efficiently. We find that DFA fails to offer more efficient scaling than backpropagation.
  arXiv  Detail & Related papers  (2022-10-26T10:09:14Z)

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.