# Multi-Agent Systems

Canonical URL: https://menfem.com/kb/harnesses/concepts/multi-agent-systems
Knowledge base topic: [Harnesses & Agent Systems](https://menfem.com/kb/harnesses)
Frontier status: active
Tags: multi-agent, collaboration, protocols

---

Multi-agent systems represent the third layer of the agentic reasoning framework — extending intelligence from individual agents to collaborative settings where multiple LLM-powered agents coordinate to solve problems. This area is rapidly evolving as standardized protocols emerge for agent-to-agent communication.

Ferrag et al. survey three key collaboration protocols that are shaping how agents interoperate: **ACP** (Agent Collaboration Protocol), **MCP** (Model Context Protocol), and **A2A** (Agent-to-Agent). These protocols define how agents discover each other's capabilities, negotiate task delegation, and share results — moving from ad-hoc multi-agent setups to standardized infrastructure.

Wei et al. frame multi-agent reasoning as "collective intelligence" — the highest layer of agentic capability, where the challenges shift from individual reasoning to coordination, negotiation, and emergent group behavior.

## Key Claims

- **Three collaboration protocols are standardizing agent interoperability** — ACP, MCP, and A2A define discovery, delegation, and result-sharing between agents. *Evidence: strong* ([From LLM Reasoning to Autonomous Agents](../../raw/llm-reasoning-to-autonomous-agents.md))
- **Multi-agent is the highest layer of agentic reasoning** — Extends foundational and self-evolving capabilities to collaborative settings. *Evidence: strong* ([Agentic Reasoning for LLMs](../../raw/agentic-reasoning-for-llms.md))
- **Governance of multi-agent systems is an open problem** — Safety, alignment, and accountability become harder with multiple autonomous agents. *Evidence: strong* ([Agentic Reasoning for LLMs](../../raw/agentic-reasoning-for-llms.md))

## Open Questions

- How to ensure safety when multiple autonomous agents interact without human oversight?
- Can standardized protocols (MCP, A2A) scale to thousands of heterogeneous agents?
- How to attribute responsibility when a multi-agent system produces harmful outputs?
- What coordination mechanisms prevent emergent adversarial dynamics between agents?

## Related Concepts

- [Agentic Reasoning](./agentic-reasoning.md) — Multi-agent is the third layer of the framework
- [LLM Tool Use](./llm-tool-use.md) — Agents use tools as part of collaborative task execution
- [Agent Evaluation Benchmarks](./agent-evaluation-benchmarks.md) — Interactive benchmarks increasingly test multi-agent scenarios

## Backlinks

*Pages that reference this concept:*
- [OpenAI](../entities/openai.md)

## Sources

- llm-reasoning-to-autonomous-agents
- agentic-reasoning-for-llms

---

Cite as: MenFem Knowledge Base — https://menfem.com/kb/harnesses/concepts/multi-agent-systems