Navigating Complexity: Orchestrated Problem Solving with Multi-Agent LLMs

TL;DR

The paper tackles the bottleneck of solving complex, vague problems with LLMs by introducing an orchestration framework that decomposes problems into subproblems and delegates them to specialized agents and non-LLM tools. An Orchestration LLM interacts with users to clarify requirements, then distributes work across domain-specific agents coordinated via LangChain. Empirical demonstrations in travel planning and exploratory research summarize show improved scalability and accuracy, with GSM8K evaluations indicating a peak 73% solve rate using GPT-4 based orchestration. The work contributes a scalable, human-inspired problem-solving paradigm and identifies future needs in generalization and adaptive agent integration.

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in solving various tasks, yet they often struggle with comprehensively addressing complex and vague problems. Existing approaches, including multi-agent LLM systems, offer solutions to certain challenges but still require manual setup and lack scalability. To address this gap, we propose a novel approach leveraging decomposition to enable LLMs to tackle vague problems effectively. Our approach involves an orchestrating LLM that interacts with users to understand the problem and then decomposes it into tangible sub-problems. Instead of expecting the LLM to solve the entire problem in one go, we train it to ask follow-up questions to gain a deeper understanding of the user's requirements. Once the problem is adequately understood, the orchestrating LLM divides it into smaller, manageable sub-problems. Each sub-problem is then assigned to specialized LLM agents or non-LLM functions for resolution. These agents work in parallel to solve their respective sub-problems, with the orchestrating LLM overseeing the process and compiling the solutions into a comprehensive answer for the user. By adopting this decomposition approach, we alleviate the constraints imposed by token limitations on LLM outputs and empower them to provide nuanced solutions to complex and ambiguous problems. Through our approach, we aim to enable LLMs to think and operate more like humans, breaking down complex problems into manageable parts and collaboratively solving them. This not only enhances the problem-solving capabilities of LLMs but also offers a scalable and efficient method for addressing a wide range of real-world challenges.