TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation

TL;DR

This paper introduces TDAG, a multi-agent framework that dynamically decomposes complex tasks into subtasks with specialized agents, improving adaptability and performance in real-world scenarios, and presents ItineraryBench for detailed evaluation.

Contribution

The paper proposes a novel multi-agent framework with dynamic task decomposition and agent generation, enhancing adaptability and performance in complex tasks.

Findings

TDAG outperforms baseline methods in adaptability and context awareness.

ItineraryBench provides fine-grained evaluation of multi-step task performance.

Experimental results demonstrate TDAG's effectiveness in complex scenarios.

Abstract

The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological constraints, such as error propagation and limited adaptability. To address this issue, we propose a multi-agent framework based on dynamic Task Decomposition and Agent Generation (TDAG). This framework dynamically decomposes complex tasks into smaller subtasks and assigns each to a specifically generated subagent, thereby enhancing adaptability in diverse and unpredictable real-world tasks. Simultaneously, existing benchmarks often lack the granularity needed to evaluate incremental progress in complex, multi-step tasks. In response, we introduce ItineraryBench in the context of travel planning, featuring interconnected, progressively complex tasks with a fine-grained evaluation system. ItineraryBench is designed to assess agents' abilities in memory, planning, and tool usage across tasks of varying complexity. Our experimental results reveal that TDAG significantly outperforms established baselines, showcasing its superior adaptability and context awareness in complex task scenarios.