Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models
Department of Computer Science and Engineering, POSTECH, South Korea(计算机科学与工程系,POSTECH,韩国);Graduate School of Artificial Intelligence, POSTECH, South Korea(人工智能研究生院,POSTECH,韩国)
Sungjae Lee, Hyejin Park, Jaechang Kim, Jungseul Ok
Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suffer from computational inefficiency and redundancy. First, they overlook the diversity of task difficulties, leading to unnecessarily extensive searches even for easy tasks. Second, they neglect the semantics of reasoning paths, resulting in redundant exploration of semantically identical paths. To address these limitations, we propose Semantic Exploration with Adaptive Gating (SEAG), a computationally efficient method. SEAG employs an adaptive gating mechanism that dynamically decides whether to conduct a tree search, based on the confidence level of answers from a preceding simple reasoning method. Furthermore, its tree-based exploration consolidates semantically identical reasoning steps, reducing redundant explorations while maintaining or even improving accuracy. Our extensive experiments demonstrate that SEAG significantly improves accuracy by 4.3% on average while requiring only 31% of computational costs compared to existing tree search-based methods on complex reasoning benchmarks including GSM8K and ARC with diverse language models such as Llama2, Llama3, and Mistral. Our code is available at https://github.com/ml-postech/SEAG-semantic-exploration-with-adaptive-gating .
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
Allen Institute for AI(艾伦人工智能研究所);School of Computer Science, Peking University(北京大学计算机学院);UCLA(加利福尼亚大学洛杉矶分校);Ohio State University(俄亥俄州立大学);UIUC(伊利诺伊大学厄巴纳-香槟分校)
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院);Institute for Advanced Study in Mathematics, Harbin Institute of Technology(哈尔滨工业大学数学研究所);School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);School of Automation, Central South University(中南大学自动化学院);College of New Energy and Materials, China University of Petroleum, Beijing(中国石油大学(北京)新能源与材料学院);College of Carbon Neutrality Future Technology, China University of Petroleum, Beijing(中国石油大学(北京)碳中和未来技术学院);DeepVerse PTE. LTD.
Do Large Language Models Truly Grasp Mathematics? An Empirical Exploration From Cognitive Psychology
College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院);Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)(科学、技术和研究局高性能计算研究所);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所)
An Improved FOX Optimization Algorithm Using Adaptive Exploration and Exploitation for Global Optimization
College of Computer Science, University of Technology(技术大学计算机科学学院);Department of Computer Science and Engineering(大学工程学院;人工智能研究所,库尔德大学);AIIC, University of Kurdistan
A multi-strategy improved gazelle optimization algorithm for solving numerical optimization and engineering applications
Zhejiang Dongfang Polytechnic(浙江东方职业技术学院);University of Glasgow(格拉斯哥大学);Columbia University(哥伦比亚大学);Universiti Malaysia Perlis(马来西亚玻璃市大学);Concordia University(康考迪亚大学)
Let Me Try Again: Examining Replay Behavior by Tracing Students' Latent Problem-Solving Pathways
University of Florida(佛罗里达大学);Worcester Polytechnic Institute(沃思黑普理工学院);Singapore University of Technology and Design(新加坡科技与设计大学);Carnegie Mellon University(卡内基梅隆大学)