Multi-Agent & Swarms
Coordination, emergence, and collective intelligence.
Why Multi-Agent
One agent hits a wall. The smart move is not a bigger agent - it is more agents.
FIPA-ACL Heritage and Speech Acts
Before MCP, before A2A, there was FIPA-ACL. In 2000 the IEEE Foundation for Intelligent Physical Agents ratified an agent communication language with twenty performatives, two c…
Communication Protocols
Agents that can't speak the same language aren't a team. They're strangers shouting into the void.
The Multi-Agent Primitive Model
Every multi-agent framework shipping in 2026 — AutoGen, LangGraph, CrewAI, OpenAI Agents SDK, Microsoft Agent Framework — is a point in a four-dimensional design space. Four pri…
Supervisor / Orchestrator-Worker Pattern
One lead agent plans and delegates; specialized workers execute in parallel contexts and report back. This is the pattern behind Anthropic's Research system (Claude Opus 4 as le…
Hierarchical Architecture and Decomposition Drift
Hierarchical is supervisor nested. Manager agents over sub-managers over workers. CrewAI `Process.hierarchical` is the textbook version: a `manager_llm` dynamically delegates ta…
Society of Mind and Multi-Agent Debate
Minsky's 1986 premise — intelligence is a society of specialists — gets rediscovered every decade. In 2023 Du et al. turned it into a concrete algorithm: multiple LLM instances …
Role Specialization — Planner / Critic / Executor / Verifier
The most common multi-agent decomposition in 2026: one agent plans, one executes, one critiques or verifies. MetaGPT (arXiv:2308.00352) formalizes this as SOPs encoded into role…
Parallel Swarm and Networked Architectures
Contrast with supervisor: no central decider. Agents read a shared event bus, pick up work asynchronously, write results back. LangGraph explicitly supports "Swarm Architecture"…
Group Chat and Speaker Selection
AutoGen GroupChat and AG2 GroupChat share one conversation across N agents; a selector function (LLM, round-robin, or custom) picks who speaks next. This is the archetype of eme…
Handoffs and Routines (Stateless Orchestration)
OpenAI's Swarm (October 2024) distilled multi-agent orchestration to two primitives: **routines** (instructions + tools as a system prompt) and **handoffs** (a tool that returns…
A2A — The Agent-to-Agent Protocol
Google announced A2A in April 2025; by April 2026 the spec is at https://a2a-protocol.org/latest/specification/ and 150+ organizations back it. A2A is the horizontal complement …
Shared Memory and Blackboard Patterns
Two approaches coexist in 2026 multi-agent systems: the **message pool** (everyone sees everyone's messages, as in AutoGen GroupChat or MetaGPT) and the **blackboard with subscr…
Consensus and Byzantine Fault Tolerance
Classical distributed-systems BFT meets stochastic LLMs. In 2025-2026 three research directions emerged: **CP-WBFT** (arXiv:2511.10400) weighs each vote by a confidence probe; *…
Voting, Self-Consistency, and Debate Topology
The cheapest aggregation: sample N independent agents, majority-vote. Wang et al. 2022 self-consistency did this with one model sampled N times. Multi-agent extends it with **he…
Negotiation and Bargaining
Agents negotiate resources, prices, task allocations, and terms. The 2026 benchmark set is clear: NegotiationArena (arXiv:2402.05863) shows LLMs can improve payoffs ~20% via per…
Generative Agents and Emergent Simulation
Park et al. 2023 (UIST '23, arXiv:2304.03442) populated **Smallville**, a sandbox of 25 agents, with a three-part architecture: **memory stream** (natural-language log), **refle…
Theory of Mind and Emergent Coordination
Li et al. (arXiv:2310.10701) showed that LLM agents in a cooperative text game exhibit **emergent high-order Theory of Mind** (ToM) — reasoning about what another agent believes…
Swarm Optimization (PSO, ACO)
Bio-inspired optimization is making an LLM comeback. **LMPSO** (arXiv:2504.09247) uses PSO where each particle's velocity is a prompt and the LLM generates the next candidate; w…
MARL — MADDPG, QMIX, MAPPO
The reinforcement-learning heritage of multi-agent coordination, which still informs LLM-agent systems in 2026. **MADDPG** (Lowe et al., NeurIPS 2017, arXiv:1706.02275) introduc…
Agent Economies, Token Incentives, Reputation
Long-horizon autonomous agents (METR's 1-hour to 8-hour work-curve) need economic agency. The emerging **5-layer stack** is: **DePIN** (physical compute) → **Identity** (W3C DID…
Production Scaling — Queues, Checkpoints, Durability
Scaling multi-agent systems to thousands of concurrent runs requires **durable execution**. LangGraph's runtime writes a checkpoint after each super-step keyed by `thread_id` (P…
Failure Modes — MAST, Groupthink, Monoculture
The reference taxonomy for 2026 is **MAST** (Cemri et al., NeurIPS 2025, arXiv:2503.13657), derived from 1642 execution traces across 7 state-of-the-art open-source MAS showing …
Evaluation and Coordination Benchmarks
Five 2025-2026 benchmarks cover the multi-agent evaluation space. **MultiAgentBench / MARBLE** (ACL 2025, arXiv:2503.01935) evaluates star/chain/tree/graph topologies with miles…
Case Studies and 2026 State of the Art
Three production-grade references to study end-to-end, each illustrating a different slice of multi-agent engineering. **Anthropic's Research system** (orchestrator-worker, 15x …