The field of artificial intelligence is witnessing significant developments in the integration of multi-agent systems and large language models. Recent research has focused on enhancing the capabilities of these systems to perform complex tasks, such as travel planning, conversational AI, and optimization problems. A key trend is the use of hierarchical and adaptive architectures to improve the flexibility and reliability of these systems. Another important area of research is the development of methods to evaluate and optimize the performance of multi-agent systems, including the use of stability-aware prompt generation and meta-design approaches. These advancements have the potential to enable more effective and efficient solutions to real-world problems. Noteworthy papers include Vaiage, which proposes a multi-agent framework for personalized travel planning, and HALO, which introduces a hierarchical autonomous logic-oriented orchestration framework for multi-agent LLM systems. Additionally, the paper on Prompt Stability Matters highlights the importance of prompt stability in building robust and effective prompt generation systems.
Advancements in Multi-Agent Systems and Large Language Models
Sources
Vaiage: A Multi-Agent Solution to Personalized Travel Planning
Connecting the Dots: A Chain-of-Collaboration Prompting Framework for LLM Agents
Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models
HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems
Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
RAG/LLM Augmented Switching Driven Polymorphic Metaheuristic Framework
Meta-Design Matters: A Self-Design Multi-Agent System
COSMIC: Enabling Full-Stack Co-Design and Optimization of Distributed Machine Learning Systems
Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories
Collaborative Problem-Solving in an Optimization Game
Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image Processing
Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development
Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning
Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design