The code written by developers usually suffers from efficiency problems and contain various performance bugs. These inefficiencies necessitate the research of automated refactoring methods for code optimization. Early research in code optimization employs rule-based methods and focuses on specific inefficiency issues, which are labor-intensive and suffer from the low coverage issue. Recent work regards the task as a sequence generation problem, and resorts to deep learning (DL) techniques such as large language models (LLMs). These methods typically prompt LLMs to directly generate optimized code. Although these methods show state-of-the-art performance, such one-step generation paradigm is hard to achieve an optimal solution. First, complex optimization methods such as combinatorial ones are hard to be captured by LLMs. Second, the one-step generation paradigm poses challenge in precisely infusing the knowledge required for effective code optimization within LLMs, resulting in under-optimized code.To address these problems, we propose to model this task from the search perspective, and propose a search-based LLMs framework named SBLLM that enables iterative refinement and discovery of improved optimization methods. SBLLM synergistically integrate LLMs with evolutionary search and consists of three key components: 1) an execution-based representative sample selection part that evaluates the fitness of each existing optimized code and prioritizes promising ones to pilot the generation of improved code; 2) an adaptive optimization pattern retrieval part that infuses targeted optimization patterns into the model for guiding LLMs towards rectifying and progressively enhancing their optimization methods; and 3) a genetic operator-inspired chain-of-thought prompting part that aids LLMs in combining different optimization methods and generating improved optimization methods.
Hugging Face;Sapienza University(罗马第一大学(萨皮恩扎大学));Leipzig University(莱比锡大学);Telefonica I+D(西班牙电信研发公司);Mavenoid;University of Copenhagen(哥本哈根大学)
ROOTS是一个1.6TB的多语言文本语料库,为BLOOM的培训而开发,目前是最大的语言模型,明确地伴随着相应的数据治理工作。在继续这些努力,我们提出了根搜索工具:一个搜索引擎在整个根语料库提供模糊和准确的搜索能力。根是迄今为止最大的语料库,可以调查这种方式。ROOTS搜索工具是开源的,可在Hugging Face Spaces上使用。我们描述了我们的实现和我们的工具的可能用例。
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Baichuan Inc.(北川公司);University of Chinese Academy of Sciences(中国科学院大学);Tongji University(同济大学);The University of Edinburgh(爱丁堡大学);Zhejiang University(浙江大学)
ReSearch 提出通过强化学习训练 LLMs 将搜索操作融入推理链,无需监督推理步骤,在 Qwen2.5 系列模型上训练后展现出跨基准的强泛化能力,并自然涌现反思与自我纠错能力。
SearchAttack: Red-Teaming LLMs against Knowledge-to-Action Threats under Online Web Search
Institute of Computing Technology, CAS(计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);People's Public Security University of China(中国人民公安大学);University of Science and Technology of China(中国科学技术大学);Guangdong Laboratory of Artificial Intelligence and Digital Economy(广东人工智能与数字经济实验室);Tsinghua University(清华大学)
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Department of Computer Science, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校计算机科学系);Center for Intelligent Information Retrieval, University of Massachusetts Amherst(马萨诸塞大学阿姆赫斯特分校智能信息检索中心);Google Cloud AI Research(谷歌云人工智能研究)
Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China(香港科技大学计算机科学与工程系);School of Law, Tsinghua University, Beijing, China(清华大学法学院);Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada(滑铁卢大学丘成桐计算机科学系)
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
University of Southern California(南加州大学);Ohio State University(俄亥俄州立大学);Fudan University(复旦大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Pittsburgh(匹兹堡大学);University of Washington(华盛顿大学);Cornell University(康奈尔大学)
Bayesian Optimization for Controlled Image Editing via LLMs
University of Edinburgh(爱丁堡大学);University of Manchester(曼彻斯特大学);University of Washington(华盛顿大学);Tsinghua University(清华大学);Skai Intelligence(Skai智能科技);University of Copenhagen(哥本哈根大学)
Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);University College London(伦敦大学学院);CSCEC Third Bureau(中建第三工程局);WeChat AI(微信AI)
SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making
Department of Industrial & Systems Engineering, University of Washington(工业与系统工程系,华盛顿大学);College of Engineering, University of Washington(工程学院,华盛顿大学);Michael G. Foster School of Business, University of Washington(Michael G. Foster商学院,华盛顿大学)