BusMA: A Bus Communication Substrate for Multi-Agent Systems
cs.AI
Submitted: 2026-09-14
Updated: 2026-09-14
Code: https://github.com/huggingface/smolagents
License: http://creativecommons.org/licenses/by/4.0/
The gist: Multi-Agent (MA) systems are effective at solving complex tasks that demand planning, tool use, and the synthesis of evidence from multiple sources.
Terminology
Abstract
Multi-Agent (MA) systems are effective at solving complex tasks that demand planning, tool use, and the synthesis of evidence from multiple sources. Existing systems typically adopt Hierarchical Manager-Worker (HMW) or Router-based Message Passing (RMP) structures as their communication protocol. However, these designs restrict agent autonomy: Worker agents cannot directly consult specific "peers", and misrouted messages can propagate errors. Inspired by bus architectures in computer systems, we propose BusMA, a communication framework that allows any agent to address other agents through a shared channel, i.e., the Bus. It consists of agent registration, message routing, and shared memory management components. Worker agents, each equipped with tools, have their own local memory and can reason, act (tool usage), and communicate by posting shared messages with specific intents. We introduce four intents: discussion, challenge, guidance, and request for explanation, which support fine-grained communication among agents. A Chair agent monitors the shared memory to coordinate interactions and facilitate convergence among Workers. To evaluate the effectiveness of BusMA, we conduct extensive experiments with two frontier LLMs across 13 tasks spanning visual reasoning, mathematical reasoning, and knowledge retrieval demonstrate that BusMA consistently outperforms state-of-the-art HMW and RMP methods.
Sources
- A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- GPT-4 Technical Report
- DeepSeek-V3 Technical Report
- ProtocolBench: Which LLM MultiAgent Protocol to Choose?
- A Survey on the Optimization of Large Language Model-based Agents
- AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need
- A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- LLM Multi-Agent Systems: Challenges and Open Problems
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
- Data Interpreter: An LLM Agent For Data Science
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
- Understanding the planning of LLM agents: A survey
- Deep Research Agents: A Systematic Examination And Roadmap
- A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives
- A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection