← Back to Research Radar
Academic Publication Academic Publication

A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges

250
Citations
October 8, 2024
Published Date

Research Abstract & Technology Focus

AbstractThe pursuit of more intelligent and credible autonomous systems, akin to human society, has been a long-standing endeavor for humans. Leveraging the exceptional reasoning and planning capabilities of large language models (LLMs), LLM-based agents have been proposed and have achieved remarkable success across a wide array of tasks. Notably, LLM-based multi-agent systems (MAS) are considered a promising pathway towards realizing general artificial intelligence that is equivalent to or surpasses human-level intelligence. In this paper, we present a comprehensive survey of these studies, offering a systematic review of LLM-based MAS. Adhering to the workflow of LLM-based multi-agent systems, we synthesize a general structure encompassing five key components: profile, perception, self-action, mutual interaction, and evolution. This unified framework encapsulates much of the previous work in the field. Furthermore, we illuminate the extensive applications of LLM-based MAS in two principal areas: problem-solving and world simulation. Finally, we discuss in detail several contemporary challenges and provide insights into potential future directions in this domain.
Read Full Literature

AI Semantic Synergy Context

Connecting this academic literature to real-world market discussions and products.

stackexchange.com › answer
0%

What are the best-practice architectural workflows for LLM-based contract compliance agents?

For LLM-based contract compliance agents, the most reliable architectures tend to combine structured document graphs, retrieval pipelines, and staged evaluation rather than relying on a single agen...

stackexchange.com › answer
0%

What are the best-practice architectural workflows for LLM-based contract compliance agents?

Designing a contract compliance agent is a high-stakes engineering task because "close enough" doesn't cut it in legal-tech. Your current dual-agent approach is a great start, but to handle the nua...

github.com › AI insight
0%

[Feature] Ollama / local model LLMAdapter

The request for an 'Ollama / local model LLMAdapter' highlights a significant market trend: the growing demand for running multi-agent workflows without 'depending on cloud APIs.' This caters direc...

news.ycombinator.com › comment
0%

Show HN: I built a tiny LLM to demystify how language models work

Cool project. I'm working on something where multiple LLM agents share a world and interact with each other autonomously. One thing that surprised me is how much the "world" matters — same model, s...

roipad.com › narrative analysis
0%

Llm-agents

The proliferation of LLM agents is driving critical discussions around their governance, security vulnerabilities like "Disregard That" attacks, and the architectural challenges of scaling distribu...

Frequently Asked Questions (FAQ)

Curated market intelligence mapped to this research.

What is the core focus of the research titled 'A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges'?

This literature focuses on: AbstractThe pursuit of more intelligent and credible autonomous systems, akin to human society, has been a long-standing endeavor for humans. Leveraging the exceptional reasoning and planning capabilities of large language models (LLMs), LLM-based...

Are there open-source GitHub repositories related to A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges?

Yes, open-source projects like THU-MAIC/OpenMAIC (Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click) are actively building upon these concepts.

Which startups are commercializing the technology behind A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges?

Products like BAND are bringing this to market. Their focus is: Coordinate and govern multi-agent work in a single chat.

How is the concept of 'A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges' being discussed by engineers on StackExchange?

Yes, highly correlated activity was mapped. An entry titled 'What are the best-practice architectural workflows for LLM-based contract compliance agents?' discusses this: For LLM-based contract compliance agents, the most reliable architectures tend to combine structured document graphs, retrieval pipelines, and stag...

How is the concept of 'A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges' being discussed by engineers on Hacker News?

Yes, highly correlated activity was mapped. An entry titled 'Show HN: I built a tiny LLM to demystify how language models work' discusses this: Cool project. I'm working on something where multiple LLM agents share a world and interact with each other autonomously. One thing that surprised ...

Cite this Market Intelligence Report

Reference our AI-mapped synergy between this research and the commercial market to instantly build authority.

Commercial Realization

Startups and Open Source tools heavily associated with the concepts explored in this paper.

  • GitHub
    THU-MAIC/OpenMAIC
    Open Multi-Agent Interactive Classroom — Get an immersive, multi-ag...
  • GitHub
    nikmcfly/MiroFish-Offline
    Offline multi-agent simulation & prediction engine. English fork of...
  • Product Hunt
    BAND
    Coordinate and govern multi-agent work in a single chat
  • Product Hunt
    LobeHub
    Your Chief Agent Operator for multi-agent work

Associated Media Narrative