MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
Paper: https://arxiv.org/abs/2407.20183 (July 29, 2024) Authors: Zehui Chen, Kuikun Liu, Qiuchen Wang, Jiangning Liu, Wenwei Zhang, Kai Chen, et al. (7 authors) Category: Agentic Search
Overview
MindSearch is an open framework that mimics how humans seek and integrate information on the web, instantiated as a simple yet effective LLM-based multi-agent system.
Motivation
Combining LLMs with search engines still underperforms because of three challenges:
1. Complex requests often cannot be accurately and completely answered by a single search-engine query. 2. The information to be integrated is spread over multiple web pages mixed with massive noise. 3. A large number of long web pages quickly exceeds the maximum context length of LLMs.
Method
Inspired by the human cognitive process, MindSearch splits the work between two agents:
- WebPlanner models multi-step information seeking as a dynamic graph construction process. It decomposes the user query into atomic sub-questions (graph nodes) and progressively extends the graph based on search results.
- WebSearcher performs hierarchical information retrieval with search engines for each sub-question and collects valuable information for the WebPlanner.
- The framework reads and integrates information from more than 300 web pages in about 3 minutes — effort equivalent to roughly 3 hours of human work.
- MindSearch shows significant improvement in response quality (depth and breadth) on both closed-set and open-set QA problems.
- In human evaluation, responses from a MindSearch instance based on InternLM2.5-7B were preferred over ChatGPT-Web and Perplexity.ai, suggesting a competitive open alternative to proprietary AI search engines.
- A Systematic Framework for Enterprise Knowledge Retrieval (arXiv:2512.05411)
- Retrieval Augmented Generation and Understanding in Vision: A Survey (arXiv:2503.18016)
- Synergizing RAG and Reasoning: A Systematic Review (arXiv:2504.15909)
- AceSearcher: Bootstrapping Reasoning and Search for LLMs via RL (arXiv:2509.24193)
- Agentic Information Retrieval (arXiv:2410.09713)
The multi-agent design allows information to be sought and integrated in parallel.
Results
Original Abstract
> Information seeking and integration is a complex cognitive task that consumes enormous time and effort. Inspired by the remarkable progress of Large Language Models, recent works attempt to solve this task by combining LLMs and search engines. However, these methods still obtain unsatisfying performance due to three challenges: (1) complex requests often cannot be accurately and completely retrieved by the search engine once (2) corresponding information to be integrated is spread over multiple web pages along with massive noise, and (3) a large number of web pages with long contents may quickly exceed the maximum context length of LLMs. Inspired by the cognitive process when humans solve these problems, we introduce MindSearch to mimic the human minds in web information seeking and integration, which can be instantiated by a simple yet effective LLM-based multi-agent framework. The WebPlanner models the human mind of multi-step information seeking as a dynamic graph construction process: it decomposes the user query into atomic sub-questions as nodes in the graph and progressively extends the graph based on the search result from WebSearcher. Tasked with each sub-question, WebSearcher performs hierarchical information retrieval with search engines and collects valuable information for WebPlanner. The multi-agent design of MindSearch enables the whole framework to seek and integrate information parallelly from larger-scale (e.g., more than 300) web pages in 3 minutes, which is worth 3 hours of human effort. MindSearch demonstrates significant improvement in the response quality in terms of depth and breadth, on both close-set and open-set QA problems. Besides, responses from MindSearch based on InternLM2.5-7B are preferable by humans to ChatGPT-Web and Perplexity.ai applications, which implies that MindSearch can already deliver a competitive solution to the proprietary AI search engine.