InterviewsVector
Original Academy

Legacy mirror · noindex · upstream phase 16

Multi-Agent & Swarms

Coordination, emergence, and collective intelligence.

Provenance: this phase outline and its lesson readings are preserved from ai-engineering-from-scratch by Rohit Ghumare under the MIT License. InterviewsVector does not claim authorship. These archive pages remain available for old links and progress, but are excluded from indexing.

Attributed readings

  1. 01Why Multi-AgentOne agent hits a wall. The smart move is not a bigger agent - it is more agents.
  2. 02FIPA-ACL Heritage and Speech ActsBefore 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…
  3. 03Communication ProtocolsAgents that can't speak the same language aren't a team. They're strangers shouting into the void.
  4. 04The Multi-Agent Primitive ModelEvery 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…
  5. 05Supervisor / Orchestrator-Worker PatternOne 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…
  6. 06Hierarchical Architecture and Decomposition DriftHierarchical is supervisor nested. Manager agents over sub-managers over workers. CrewAI `Process.hierarchical` is the textbook version: a `manager_llm` dynamically delegates ta…
  7. 07Society of Mind and Multi-Agent DebateMinsky'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 …
  8. 08Role Specialization — Planner / Critic / Executor / VerifierThe 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…
  9. 09Parallel Swarm and Networked ArchitecturesContrast with supervisor: no central decider. Agents read a shared event bus, pick up work asynchronously, write results back. LangGraph explicitly supports "Swarm Architecture"…
  10. 10Group Chat and Speaker SelectionAutoGen 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…
  11. 11Handoffs 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…
  12. 12A2A — The Agent-to-Agent ProtocolGoogle 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 …
  13. 13Shared Memory and Blackboard PatternsTwo 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…
  14. 14Consensus and Byzantine Fault ToleranceClassical 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; *…
  15. 15Voting, Self-Consistency, and Debate TopologyThe 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…
  16. 16Negotiation and BargainingAgents 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…
  17. 17Generative Agents and Emergent SimulationPark 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…
  18. 18Theory of Mind and Emergent CoordinationLi 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…
  19. 19Swarm 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…
  20. 20MARL — MADDPG, QMIX, MAPPOThe 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…
  21. 21Agent Economies, Token Incentives, ReputationLong-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…
  22. 22Production Scaling — Queues, Checkpoints, DurabilityScaling 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…
  23. 23Failure Modes — MAST, Groupthink, MonocultureThe 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 …
  24. 24Evaluation and Coordination BenchmarksFive 2025-2026 benchmarks cover the multi-agent evaluation space. **MultiAgentBench / MARBLE** (ACL 2025, arXiv:2503.01935) evaluates star/chain/tree/graph topologies with miles…
  25. 25Case Studies and 2026 State of the ArtThree production-grade references to study end-to-end, each illustrating a different slice of multi-agent engineering. **Anthropic's Research system** (orchestrator-worker, 15x …