S*: Test Time Scaling for Code Generation

• URL: http://arxiv.org/abs/2502.14382v1
• Date: Thu, 20 Feb 2025 09:18:53 GMT
• Title: S*: Test Time Scaling for Code Generation
• Authors: Dacheng Li, Shiyi Cao, Chengkun Cao, Xiuyu Li, Shangyin Tan, Kurt Keutzer, Jiarong Xing, Joseph E. Gonzalez, Ion Stoica,
• Abstract summary: We propose S*, the first hybrid test-time scaling framework for code generation. S* substantially improves the coverage and selection accuracy of generated code.
• Score: 55.11863577956177
• License:
• Abstract: Increasing test-time compute for LLMs shows promise across domains but remains underexplored in code generation, despite extensive study in math. In this paper, we propose S*, the first hybrid test-time scaling framework that substantially improves the coverage and selection accuracy of generated code. S* extends the existing parallel scaling paradigm with sequential scaling to push performance boundaries. It further leverages a novel selection mechanism that adaptively generates distinguishing inputs for pairwise comparison, combined with execution-grounded information to robustly identify correct solutions. We evaluate across 12 Large Language Models and Large Reasoning Model and show: (1) S* consistently improves performance across model families and sizes, enabling a 3B model to outperform GPT-4o-mini; (2) S* enables non-reasoning models to surpass reasoning models - GPT-4o-mini with S* outperforms o1-preview by 3.7% on LiveCodeBench; (3) S* further boosts state-of-the-art reasoning models - DeepSeek-R1-Distill-Qwen-32B with S* achieves 85.7% on LiveCodeBench, approaching o1 (high) at 88.5%. Code will be available under https://github.com/NovaSky-AI/SkyThought.

Related papers

• Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? [61.85289698610747]
  We study whether o1-like large language models (LLMs) truly possess test-time scaling capabilities. We find that longer CoTs of these o1-like models do not consistently enhance accuracy. We propose Shortest Majority Vote, a method that combines parallel scaling strategies with CoT length characteristics.
  arXiv  Detail & Related papers  (2025-02-17T07:21:11Z)
• s1: Simple test-time scaling [148.4204982041058]
  Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. We seek the simplest approach to achieve test-time scaling and strong reasoning performance.
  arXiv  Detail & Related papers  (2025-01-31T18:48:08Z)
• SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer [50.04304674778762]
  This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. We introduce three key innovations: Efficient Training Scaling, Model Depth Pruning, and Inference-time Scaling. Through these strategies, SANA-1.5 achieves a text computation-image alignment score of 0.72 on GenEval, which can be further improved to 0.80 through inference scaling.
  arXiv  Detail & Related papers  (2025-01-30T15:31:48Z)
• Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training [3.195234044113248]
  We propose textscNeuroAL, a emphtop-up algorithm for network pruning. It modifies the block-wise and row-wise sparsity exploiting information from both the dense model and its sparse version. It consistently outperforms the latest state-of-the-art methods in terms of performance-runtime trade-off.
  arXiv  Detail & Related papers  (2024-11-11T15:30:16Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition [19.905455701387194]
  We present an efficient Graph Convolutional Network (GCN) baseline for skeleton-based action recognition. On two large-scale datasets, i.e., NTU RGB+D 60 and 120, the proposed EfficientGCN-B4 baseline outperforms other State-Of-The-Art (SOTA) methods.
  arXiv  Detail & Related papers  (2021-06-29T07:09:11Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• Developing and Improving Risk Models using Machine-learning Based Algorithms [6.245537312562826]
  The objective of this study is to develop a good risk model for classifying business delinquency. The rationale under the analyses is firstly to obtain good base binary classifiers via regularization. Two model ensembling algorithms including bagging and boosting are performed on the good base classifiers for further model improvement.
  arXiv  Detail & Related papers  (2020-09-09T20:38:00Z)

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.