It is a framework designed to unify and optimize human-designed prompt engineering techniques for improving problem-solving capabilities of Large Language Models (LLMs) by representing LLM-based agents as computational graphs.
It is a framework designed to unify and optimize human-designed prompt engineering techniques for improving problem-solving capabilities of Large Language Models (LLMs) by representing LLM-based agents as computational graphs. Each node in the graph implements a function to process multimodal data or query other LLMs, while edges describe the flow of information between operations and agents. These graphs can be recursively combined into larger composite graphs, enabling hierarchies of inter-agent collaboration. The framework introduces novel automatic graph optimizers that refine node-level LLM prompts (node optimization) and improve agent orchestration by altering graph connectivity (edge optimization). Experiments show that this approach efficiently develops, integrates, and automatically enhances diverse LLM agents.
The project is led by a team of researchers and engineers affiliated with the KAUST AI Initiative and IDSIA, including PhD students, a research engineer lead, and scientific directors. Key contributors include Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. The team is based at KAUST AI Initiative (Building 12, 3rd floor) in Thuwal, Saudi Arabia, and can be contacted via official email ([email protected]) or personal emails provided for team members. The framework, referred to as GPTSwarm, aims to advance the development and optimization of LLM-based agents through collaborative and hierarchical computational structures.
It is an AI-driven initiative focused on developing advanced systems that assist in creating and editing software by translating human ideas into functional code.
It is a 124-billion-parameter open-weights multimodal model called Pixtral Large, built on Mistral Large 2, designed to excel in both image and text understanding.
It is a Python-based project called Teenage-AGI that enhances an AI agent's capabilities by giving it memory and the ability to "think" before generating responses.
It is a Python-based project called Teenage-AGI that enhances an AI agent's capabilities by giving it memory and the ability to "think" before generating responses.
It is an open-source framework designed to provide AI Agents with reliable memory capabilities for decision-making, personalized goal setting, and execution in AI applications.
It is an open-source multi-agent framework called CAMEL, dedicated to finding the scaling laws of agents by studying their behaviors, capabilities, and potential risks on a large scale.
It is an experimental open-source project called Multi-GPT, designed to make GPT-4 fully autonomous by enabling multiple specialized AI agents, referred to as "expertGPTs," to collaborate on tasks.
It is a recommender system simulator called Agent4Rec, designed to explore the potential of large language model (LLM)-empowered generative agents in simulating human-like behavior in recommendation environments.
It is a platform designed to build and deploy AI agents that address trust barriers in adopting agentic AI by embedding data protection, policy enforcement, and validation into every agent, ensuring business success.
It is a project titled "Natural Language-Based Societies of Mind (NLSOM)" that explores the concept of intelligence through diverse, interconnected agents working collaboratively in a natural language-based framework.
It is a preliminary implementation of the paper "Improving Factuality and Reasoning in Language Models through Multiagent Debate," which aims to enhance the accuracy and reasoning capabilities of language models by employing a multiagent debate framework.
It is an implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4," a project designed to develop an AI agent capable of playing imperfect information games using GPT-4 enhanced with Theory of Mind (ToM) awareness.
It is a marketplace designed for discovering, comparing, and connecting with powerful AI agents to help businesses streamline operations, reduce costs, and drive growth.
It is a platform that automates and optimizes business workflows using specialized small language models (SLMs) to deliver accurate, efficient, and task-focused AI solutions.
It is a platform designed for Sales, Revenue Operations (RevOps), and Go-to-Market teams, offering AI-powered digital workers that automate and transform business operations.
It is an AI platform designed to provide precision, reliability, and control in generative AI (GenAI) solutions for government departments, police forces, law firms, and critical national infrastructure providers.
It is an AI-powered speech synthesis platform called LMNT that delivers ultrafast, lifelike AI speech for applications such as conversational apps, games, and virtual agents.
It is a generative AI automation platform designed to simplify the creation, deployment, and management of AI agents without requiring coding expertise.
It is an AI-powered project management tool designed to handle routine project tasks, enabling teams to focus on strategic goals and human-centric work.
It is an AI software engineer designed to assist and collaborate with human engineers by autonomously handling complex engineering tasks, allowing teams to focus on more ambitious goals.
