AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
arXiv:2308.08155
Abstract
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
arXiv comment43 pages (10 pages for the main text, 3 pages for references, and 30 pages for appendices)
Cited by in corpus (11)
- Large Language Models (LLMs) as Agents for Augmented Democracy
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
- Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency
- Validation Requirements for AI-based Intervention-Evaluation in Aging and Longevity Research and Practice
- ChainBuddy: An AI Agent System for Generating LLM Pipelines
- Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents
- LAMBDA: A Large Model Based Data Agent
- Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking
- Flows: Building Blocks of Reasoning and Collaborating AI
- Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
- A Roadmap for Tamed Interactions with Large Language Models