Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilites can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models' own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.
Sentiment Analysis based Multi-person Multi-criteria Decision Making Methodology using Natural Language Processing and Deep Learning for Smarter Decision Aid. Case study of restaurant choice using TripAdvisor reviews
Andalusian Research Institute in Data Science and Computational Intelligence(安达卢西亚数据科学与计算智能研究所);University of Granada(格拉纳达大学)
Smarter edits? Post-editing with error highlights and translation suggestions
Leiden University Centre for Linguistics(莱顿大学语言研究中心);Visvesvaraya National Institute of Technology(维什瓦塞拉亚国家理工学院);Department of Bionanoscience, Faculty of Applied Sciences, Delft University of Technology(应用科学学院生物纳米科学系,代尔夫特理工大学);Pedagogical Sciences, Leiden University(莱顿大学教育科学);Faculty of Science, Leiden University(莱顿大学科学学院)
Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing
Nanjing University of Science and Technology(南京理工大学);C 2 \text{C}^{2} DL, Institute of Automation, Chinese Academy of Sciences(C2 DL,自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Computer Science, University of Sydney(悉尼大学计算机学院)
Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
Institute of Digital Twin, Eastern Institute of Technology(数字孪生研究所、东部技术研究院);University of Science and Technology of China(中国科学技术大学);The Hong Kong University of Science and Technology(香港科技大学)
Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimation
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);University of Science and Technology of China(中国科学技术大学);China University of Mining and Technology(中国矿业大学)
Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing
Communication Systems Group CSG, Department of Informatics IfI, University of Zurich UZH, 8050 Zürich, Switzerland(苏黎世大学信息学院通信系统组);Volvo Car Corporation, 405 31 Göteborg, Sweden(沃尔沃汽车公司)
MANBench: Is Your Multimodal Model Smarter than Human?
School of Electronic Information and Communications, Huazhong University of Science and Technology(电子信息与通讯学院,华中科技大学);School of Basic Medicine, Huazhong University of Science and Technology(基础医学院,华中科技大学)
Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系)
Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Beijing Key Laboratory of Research on Large Models and Intelligent Governance(北京大模型与智能治理研究重点实验室);Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE(教育部新一代智能搜索与推荐工程研究中心);Tencent Jarvis Lab(腾讯杰维斯实验室);Medical Artificial Intelligence Lab, Westlake University(西湖大学医学人工智能实验室)
Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education
Chosun University(昌原大学);Korea University(韩国大学);Seoul National University(首尔国立大学);Korea Institute for Curriculum and Evaluation(韩国课程与评价研究院);Upstage;Indiana University Bloomington(印第安纳大学布卢明顿分校);Nanyang Technological University(南洋理工大学)