Social category
Collaboration
Who decides who works next — supervisors, handoffs, shared workspaces.
Supervisor
One decides. Specialists do.
A central agent dynamically decides which specialized agent or tool works next.
Trade-off Clear operational control is maintained at the cost of a potential coordination bottleneck.
Hierarchical Supervisor
Supervisors of supervisors. Scale by layers.
Multiple supervisors organize agents in hierarchical layers, delegating responsibility for larger teams or complex domains.
Trade-off Scalable organizational structure is achieved against higher complexity and longer decision paths.
Handoff
One agent yields. Another takes over.
An agent completely transfers control and relevant context to another specialist.
Trade-off Clear transfer of responsibility is achieved at the risk of losing vital context during the handoff.
Swarm
Local rules. Global emergence. No center.
Agents coordinate decentrally via local rules, messages, and handoffs, allowing the execution path to emerge at runtime.
Trade-off High adaptability is gained at the cost of lower predictability and difficult debugging.
Group Chat
A shared thread. Everyone speaks.
Agents communicate in a shared conversation space, building upon each other's inputs in a round-robin, random, or simultaneous manner.
Trade-off Rich interaction is gained against high token costs and difficult flow control.
Multi-Agent Debate
Argue the answer. An arbiter decides.
Agents represent different positions and critically negotiate outcomes before a final decision is synthesized.
Trade-off Rigorous verification of difficult decisions is achieved against increased effort and the risk of over-arguing.
Magentic
Plan. Delegate. Synthesize. Over long horizons.
An orchestra of specialized agents combines planning, a task ledger, delegation, and replanning for long-running, complex goals.
Trade-off Massive task coverage is gained against exceptionally high operational and orchestration complexity.
Blackboard
A shared scratchpad. Specialists react.
Agents coordinate indirectly via a shared state surface where results, hypotheses, and tasks are deposited rather than using direct chat.
Trade-off Highly decoupled collaboration is achieved against demanding state management and consistency requirements.
Contract Net
Broadcast. Bid. Award. Execute.
Coordination occurs via bidding or price signals, where an agent broadcasts a task and others bid based on their capabilities, cost, or utility.
Trade-off Scalable and flexible resource allocation is gained against the difficult design of incentive and auction structures.
Agents-as-Tools
Call a specialist like any other tool.
One orchestrating agent calls other agents exactly like tools, hiding their internal logic and coordination behind a standard tool interface.
Trade-off Excellent encapsulation is achieved against limited independence for the sub-agents.
Graph-based Orchestration
An executable graph of agents, tools, and state.
Agent coordination, tools, and state transitions are modeled as an explicit, executable state graph consisting of nodes and edges. It composes the two workflow relaxations — conditional edges (Routing) and bounded cycles (Loop) — over a closed node set with a validated state schema.
Trade-off Extreme predictability and controllability are gained against significant modeling overhead.
Exploration & Discovery
Map the space. Cluster, select, deep-dive, synthesize.
A research agent maps a knowledge space, clusters findings, selects leads by novelty, impact, and feasibility, deep-dives into the promising ones, and synthesizes a cited report — coordinated as an orchestrator over parallel search and subtopic agents.
Trade-off Breadth, novelty, and synthesis quality are gained at a high token and latency cost; it needs strong stopping criteria to avoid unbounded exploration.
Where to next