K2-Think: A Parameter-Efficient Reasoning System

• URL: http://arxiv.org/abs/2509.07604v3
• Date: Mon, 15 Sep 2025 03:29:27 GMT
• Title: K2-Think: A Parameter-Efficient Reasoning System
• Authors: Zhoujun Cheng, Richard Fan, Shibo Hao, Taylor W. Killian, Haonan Li, Suqi Sun, Hector Ren, Alexander Moreno, Daqian Zhang, Tianjun Zhong, Yuxin Xiong, Yuanzhe Hu, Yutao Xie, Xudong Han, Yuqi Wang, Varad Pimpalkhute, Yonghao Zhuang, Aaryamonvikram Singh, Xuezhi Liang, Anze Xie, Jianshu She, Desai Fan, Chengqian Gao, Liqun Ma, Mikhail Yurochkin, John Maggs, Xuezhe Ma, Guowei He, Zhiting Hu, Zhengzhong Liu, Eric P. Xing,
• Abstract summary: K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model.<n>Our system shows that smaller models can compete at the highest levels by combining advanced post-training and test-time techniques.<n>K2-Think is freely available at k2think.ai, offering best-in-class inference speeds of over 2,000 tokens per second per request.
• Score: 80.62468969966133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1. Built on the Qwen2.5 base model, our system shows that smaller models can compete at the highest levels by combining advanced post-training and test-time computation techniques. The approach is based on six key technical pillars: Long Chain-of-thought Supervised Finetuning, Reinforcement Learning with Verifiable Rewards (RLVR), Agentic planning prior to reasoning, Test-time Scaling, Speculative Decoding, and Inference-optimized Hardware, all using publicly available open-source datasets. K2-Think excels in mathematical reasoning, achieving state-of-the-art scores on public benchmarks for open-source models, while also performing strongly in other areas such as Code and Science. Our results confirm that a more parameter-efficient model like K2-Think 32B can compete with state-of-the-art systems through an integrated post-training recipe that includes long chain-of-thought training and strategic inference-time enhancements, making open-source reasoning systems more accessible and affordable. K2-Think is freely available at k2think.ai, offering best-in-class inference speeds of over 2,000 tokens per second per request via the Cerebras Wafer-Scale Engine.

Related papers

• A Technical Report on the Second Place Solution for the CIKM 2025 AnalytiCup Competition [11.41948435879935]
  This work addresses the challenge of multilingual category relevance judgment in e-commerce search.<n>We propose a framework that leverages prompt engineering with Chain-of-Thought task decomposition.<n> Experimental results show that our single-model framework achieves competitive accuracy and high inference efficiency.
  arXiv  Detail & Related papers  (2025-10-25T16:31:21Z)
• A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning [57.727084580884075]
  Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
  arXiv  Detail & Related papers  (2025-09-26T08:27:03Z)
• Thinking While Listening: Simple Test Time Scaling For Audio Classification [61.3564313676731]
  We propose a framework that enables neural models to "think while listening" to everyday sounds, thereby enhancing audio classification performance.<n>Motivated by recent advances in the reasoning capabilities of large language models, we address two central questions: (i) how can thinking be incorporated into existing audio classification pipelines to enable reasoning in the category space and improve performance, and (ii) can a new architecture be designed from the ground up to support both thinking and test-time scaling.
  arXiv  Detail & Related papers  (2025-09-24T01:17:24Z)
• KAT-V1: Kwai-AutoThink Technical Report [50.84483585850113]
  We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks.<n>KAT dynamically switches between reasoning and non-reasoning modes based on task complexity.<n>We also propose Step-SRPO, a reinforcement learning algorithm that incorporates intermediate supervision into the GRPO framework.
  arXiv  Detail & Related papers  (2025-07-11T04:07:10Z)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models [39.56594737760323]
  PTSBench is the first comprehensive post-training sparsity benchmark towards algorithms and models.<n>We benchmark 10+ PTS general-pluggable fine-grained techniques on 3 typical tasks using over 40 off-the-shelf model architectures.<n>Our PTSBench can provide (1) new observations for a better understanding of the PTS algorithms, (2) in-depth and comprehensive evaluations for the sparsification ability of models, and (3) a well-structured and easy-integrate open-source framework.
  arXiv  Detail & Related papers  (2024-12-10T07:49:07Z)
• The THUEE System Description for the IARPA OpenASR21 Challenge [12.458730613670316]
  This paper describes the THUEE team's speech recognition system for the IARPA Open Automatic Speech Recognition Challenge (OpenASR21) We achieve outstanding results under both the Constrained and Constrained-plus training conditions. We find that the feature extractor plays an important role when applying the wav2vec2.0 pre-trained model to the encoder-decoder based CTC/Attention ASR architecture.
  arXiv  Detail & Related papers  (2022-06-29T14:03:05Z)
• DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models [152.29364079385635]
  As pre-trained models grow bigger, the fine-tuning process can be time-consuming and computationally expensive. We propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning and (ii) resource-efficient inference.
  arXiv  Detail & Related papers  (2021-10-30T03:29:47Z)

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.