Towards AI Search Paradigm
Abstract
In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-making. The paradigm employs a modular architecture of four LLM-powered agents (Master, Planner, Executor and Writer) that dynamically adapt to the full spectrum of information needs, from simple factual queries to complex multi-stage reasoning tasks. These agents collaborate dynamically through coordinated workflows to evaluate query complexity, decompose problems into executable plans, and orchestrate tool usage, task execution, and content synthesis. We systematically present key methodologies for realizing this paradigm, including task planning and tool integration, execution strategies, aligned and robust retrieval-augmented generation, and efficient LLM inference, spanning both algorithmic techniques and infrastructure-level optimizations. By providing an in-depth guide to these foundational components, this work aims to inform the development of trustworthy, adaptive, and scalable AI search systems.
Cite
@article{arxiv.2506.17188,
title = {Towards AI Search Paradigm},
author = {Yuchen Li and Hengyi Cai and Rui Kong and Xinran Chen and Jiamin Chen and Jun Yang and Haojie Zhang and Jiayi Li and Jiayi Wu and Yiqun Chen and Changle Qu and Wenwen Ye and Lixin Su and Xinyu Ma and Lingyong Yan and Long Xia and Daiting Shi and Junfeng Wang and Xiangyu Zhao and Jiashu Zhao and Haoyi Xiong and Shuaiqiang Wang and Dawei Yin},
journal= {arXiv preprint arXiv:2506.17188},
year = {2026}
}