LLM test-time compute (or LLM inference) via search has emerged as a promising research area with rapid developments. However, current frameworks often adopt distinct perspectives on three key aspects: task definition, LLM profiling, and search procedures, making direct comparisons challenging. Moreover, the search algorithms employed often diverge from standard implementations, and their specific characteristics are not thoroughly specified. This survey aims to provide a comprehensive but integrated technical review on existing LIS frameworks. Specifically, we unify task definitions under Markov Decision Process (MDP) and provides modular definitions of LLM profiling and search procedures. The definitions enable precise comparisons of various LLM inference frameworks while highlighting their departures from conventional search algorithms. We also discuss the applicability, performance, and efficiency of these methods. For ongoing paper updates, please refer to our GitHub repository: https://github.com/xinzhel/LLM-Search.
CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
Department of Electrical and Computer Engineering, The University of Hong Kong（香港大学电子与计算机工程系）；School of Computing and Data Science, The University of Hong Kong（香港大学计算与数据科学学院）；School of Biomedical Engineering, The University of Hong Kong（香港大学生物医学工程学院）；Nvidia AI Technology Center（NVIDIA人工智能技术中心）；Advanced Biomedical Instrumentation Centre（先进生物医学仪器中心）
PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
Centre for Industrial Software, University of Southern Denmark（丹麦南部大学工业软件中心）；Department of Electronics, Information and Bioengineering, Politecnico di Milano（米兰理工学院电子、信息与生物工程系）
SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference
The University of Sydney（悉尼大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Shanghai Jiao Tong University（上海交通大学）；NVIDIA（英伟达）；The University of Hong Kong（香港大学）
