XAgents: A Unified Framework for Multi-Agent Cooperation via IF-THEN Rules and Multipolar Task Processing Graph

2025-09-12

AI Summary

To address planning failures and coordination breakdowns in multi-agent systems (MAS) operating under high complexity and strong uncertainty, this paper proposes a unified collaborative framework. The framework employs a multi-pole task-processing graph for dynamic task decomposition and scheduling, integrates domain-specific and globally coordinated IF-THEN rule engines, embeds large language model (LLM)-based agents, and incorporates dynamic subtask allocation with real-time state feedback. This design significantly enhances planning robustness and inter-agent coordination accuracy. Extensive experiments on three knowledge-intensive and logic-driven question-answering datasets demonstrate consistent superiority over state-of-the-art single-agent and multi-agent baselines. Results validate the framework’s effectiveness in executing complex tasks under uncertainty and confirm its strong generalization capability across diverse reasoning-intensive domains.

Technology Category

• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rapid advancement of Large Language Models (LLMs) has significantly enhanced the capabilities of Multi-Agent Systems (MAS) in supporting humans with complex, real-world tasks. However, MAS still face challenges in effective task planning when handling highly complex tasks with uncertainty, often resulting in misleading or incorrect outputs that hinder task execution. To address this, we propose XAgents, a unified multi-agent cooperative framework built on a multipolar task processing graph and IF-THEN rules. XAgents uses the multipolar task processing graph to enable dynamic task planning and handle task uncertainty. During subtask processing, it integrates domain-specific IF-THEN rules to constrain agent behaviors, while global rules enhance inter-agent collaboration. We evaluate the performance of XAgents across three distinct datasets, demonstrating that it consistently surpasses state-of-the-art single-agent and multi-agent approaches in both knowledge-typed and logic-typed question-answering tasks. The codes for XAgents are available at: https://github.com/AGI-FHBC/XAgents.

Problem

• Addresses multi-agent task planning under uncertainty
• Enhances agent cooperation using dynamic task graphs
• Integrates domain-specific rules to constrain agent behaviors

Innovation

• Multipolar task graph for dynamic planning
• IF-THEN rules constrain agent behaviors
• Global rules enhance inter-agent collaboration