Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling

• URL: http://arxiv.org/abs/2602.01208v1
• Date: Sun, 01 Feb 2026 12:57:36 GMT
• Title: Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling
• Abstract summary: textbfChronos is a chronological reasoning scorer that models each trajectory as a time series.<n>Chronos consistently delivers substantial gains across a variety of models, with negligible computational overhead.
• Score: 13.419095400140913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-Time Scaling (TTS) has emerged as an effective paradigm for improving the reasoning performance of large language models (LLMs). However, existing methods -- most notably majority voting and heuristic token-level scoring -- treat reasoning traces or tokens equally, thereby being susceptible to substantial variations in trajectory quality and localized logical failures. In this work, we introduce \textbf{Chronos}, a lightweight and plug-and-play chronological reasoning scorer that models each trajectory as a time series. Specifically, Chronos learns to capture trajectory features of token probabilities, assigns quality scores accordingly, and employs a weighted voting mechanism. Extensive evaluations on both in-domain and out-of-domain benchmarks demonstrate that Chronos consistently delivers substantial gains across a variety of models, with negligible computational overhead. Notably, Chronos@128 achieves relative improvements of 34.21\% over Pass@1 and 22.70\% over Maj@128 on HMMT25 using Qwen3-4B-Thinking-2507, highlighting its effectiveness.

Related papers

• Test-Time Scaling via Error Localization [15.13459650752427]
  Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models.<n>We introduce Test-Time Scaling via Error Localization (TTEL), an inference-time algorithm that utilizes fixed or environment feedback to perform token-level error localization.
  arXiv  Detail & Related papers  (2026-07-23T15:55:29Z)
• Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series [17.242128977027246]
  Time Series Classification (TSC) is a long-standing research problem that has gained increasing attention in recent years.<n>We propose PDFTime, a prototype-guided framework that reformulates time series classification as a multi-stage decision process.<n>To our knowledge, PDFTime is the first framework to reformulate time series classification as a decoupled, multi-stage similarity-based reasoning process.
  arXiv  Detail & Related papers  (2026-05-21T06:45:50Z)
• dVoting: Fast Voting for dLLMs [71.572316901001]
  Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling.<n>dLLMs can generate tokens at arbitrary positions in parallel, endowing them with significant potential for parallel test-time scaling.<n>We introduce dVoting, a fast voting technique that boosts reasoning capability without training, with only an acceptable extra computational overhead.
  arXiv  Detail & Related papers  (2026-02-12T16:35:05Z)
• Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling [19.080366193748127]
  Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces.<n>The combination of lengthy reasoning traces with multiple sampling introduces substantial computation and high end-to-end latency.<n>We propose STEP: Step-level Trace Evaluation and Pruning, a novel pruning framework that evaluates reasoning steps using hidden states.
  arXiv  Detail & Related papers  (2026-01-14T02:54:55Z)
• Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations [83.93566096400723]
  We find that instruction-tuned models retain up to 93.4% of their original performance when given a randomly sampled tokenization.<n>Character-level segmentation improves string manipulation and code understanding tasks by up to +14%.<n>Right-aligned digit grouping enhances large-number arithmetic by +33%.
  arXiv  Detail & Related papers  (2025-06-23T18:02:26Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• Sample, Don't Search: Rethinking Test-Time Alignment for Language Models [55.2480439325792]
  We introduce QAlign, a new test-time alignment approach.<n>As we scale test-time compute, QAlign converges to sampling from the optimal aligned distribution for each individual prompt.<n>By adopting recent advances in Markov chain Monte Carlo for text generation, our method enables better-aligned outputs without modifying the underlying model or even requiring logit access.
  arXiv  Detail & Related papers  (2025-04-04T00:41:40Z)
• Exploring Temporally-Aware Features for Point Tracking [58.63091479730935]
  Chrono is a feature backbone specifically designed for point tracking with built-in temporal awareness.<n>Chrono achieves state-of-the-art performance in a refiner-free setting on the TAP-Vid-DAVIS and TAP-Vid-Kinetics datasets.
  arXiv  Detail & Related papers  (2025-01-21T15:39:40Z)
• Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion [18.51546761241817]
  We introduce Booster, the first data augmentation strategy for temporal knowledge graphs.<n>We propose a hierarchical scoring algorithm based on triadic closures within TKGs.<n>We also propose a two-stage training approach to identify samples that deviate from the model's preferred patterns.
  arXiv  Detail & Related papers  (2024-12-31T03:47:19Z)
• Contrastive Learning Is Not Optimal for Quasiperiodic Time Series [4.2807943283312095]
  We introduce Distilled Embedding for Almost-Periodic Time Series (DEAPS) in this paper. DEAPS is a non-contrastive method tailored for quasiperiodic time series, such as electrocardiogram (ECG) data. We demonstrate a notable improvement of +10% over existing SOTA methods when just a few annotated records are presented to fit a Machine Learning (ML) model.
  arXiv  Detail & Related papers  (2024-07-24T08:02:41Z)
• Chronos: Learning the Language of Time Series [79.38691251254173]
  Chronos is a framework for pretrained probabilistic time series models. We show that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks.
  arXiv  Detail & Related papers  (2024-03-12T16:53:54Z)

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.