Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for additional training. We identify two core challenges for such systems: (i) efficiently generating diverse, high-quality candidate solutions, and (ii) reliably selecting correct answers in the absence of ground-truth supervision. To address these challenges, we propose Test-time Recursive Thinking (TRT), an iterative self-improvement framework that conditions generation on rollout-specific strategies, accumulated knowledge, and self-generated verification signals. Using TRT, open-source models reach 100% accuracy on AIME-25/24, and on LiveCodeBench's most difficult problems, closed-source models improve by 10.4-14.8 percentage points without external feedback.
Unlocking Recursive Thinking of LLMs: Alignment via Refinement
Soochow University(苏州大学);Zhipu AI(智谱AI);Tsinghua University(清华大学);Key Laboratory of Data Intelligence and Advanced Computing, Soochow University(苏州大学数据智能与先进计算重点实验室)
PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking
Center for Computational Science and Engineering(计算科学与工程中心);Schmarzman College of Computing(施马茨曼计算学院);Laboratory for Atomistic and Molecular Mechanics (LAMM)(原子与分子力学实验室);Massachusetts Institute of Technology(麻省理工学院)
LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews
Ubiquitous Knowledge Processing Lab, Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt(德意志联邦共和国达姆施塔特技术大学);School of Computing Technologies, Royal Melbourne Institute of Technology, Australia(澳大利亚皇家墨尔本理工学院);Data Science Group, University of Hamburg(汉堡大学);Department of Data Science & AI, Monash University, Australia(澳大利亚墨尔本大学)
Reviewing the Reviewer: LLM-Assisted Reviewer Feedback Generation for Guideline Compliance
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany(技术大学达姆施塔特计算机科学系 Ubiquitous Knowledge Processing Lab(UKP Lab)及国家应用网络安全研究中心 ATHENE,德国);Department of Data Science & AI, Monash University, Australia(墨尔本大学数据科学与人工智能系,澳大利亚);Data Science Group, University of Hamburg(汉堡大学数据科学组)
Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
University of Oklahoma(俄克拉荷马大学);Stanford University(斯坦福大学);School of Electrical and Computer Engineering, Oklahoma State University(电气与计算机工程学院,俄克拉荷马州立大学);University of Glasgow(格拉斯哥大学)
Toward LLM-Supported Automated Assessment of Critical Thinking Subskills
University of Minnesota(明尼苏达大学);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Adelaide University(阿德莱德大学);Brighter Research(Brighter研究公司);Educational Testing Service (ETS)(教育考试服务中心(ETS))