Agents on the Web
Visions of Agents on the Web
The vision of intelligent agents on the Web is almost as old as the Web itself: in a keynote at WWW'94, Sir Tim Berners-Lee was noting that documents on the Web describe real objects and relationships among them, and if the semantics of these objects are represented explicitly then machines can browse through and manipulate reality. This vision was articulated more fully in the 2001 Semantic Web paper [[SEMWEB01]] and is now closer to realization through the standardization of the Web of Things at the W3C and the IETF.
In the AI community, the vision of a world-wide open network of intelligent agents also emerged in the '90s. In 2002, the AgentCities initiative was reporting a network of 41 agent platforms deployed in 21 countries [[WILLMOTT02]], which grew to 60 registered platforms in 2003 [[DALE03]] and 160 by 2005 [[JADE]]. This network was based on standards developed by the Foundation for Intelligent Physical Agents (FIPA) but declined after the mid-2000s as industry attention shifted toward Web services. In parallel with AgentCities, the DARPA Control of Agent-Based Systems (CoABS) research program investigated the control, coordination, and management of large systems of autonomous software agents in military applications. Its central middleware, the CoABS Grid [[COABS1]], integrated heterogeneous agent-based systems, object-based applications, and legacy systems.
The DARPA CoABS program demonstrated the practical utility of agent technologies in large-scale deployments, while also highlighting significant challenges — for example, enabling agents to dynamically identify and interpret information sources [[COABS2]]. To address such issues, DARPA launched the Agent Markup Language (DAML) research program, which extended existing Web standards and laid the groundwork for the Web Ontology Language (OWL), Semantic Markup for Web Services (OWL-S), and other cornerstones of the Semantic Web. The DAML program advanced the original vision of the Web as an information space for both people and intelligent agents, and encouraged a shift from custom-built MAS middleware (e.g., CoABS Grid or FIPA platforms) to leveraging the Web's existing infrastructure. Such Web-based MAS received significant attention over the years, especially in the early 2000s with the advent of service-oriented computing [[SINGH06]].
Recent years have brought renewed interest in Web-based MAS — as evidenced by the Dagstuhl Seminar 21072 (Feb. 2021) and Dagstuhl Seminar 23081 (Feb. 2023) on "Agents on the Web", which led to the creation of the W3C Autonomous Agents on the Web (WebAgents) Community Group. A key enabler for this renewed interest is the Web of Things, which provides new practical use cases for Web agents and realizes several visionary ideas anticipated in the original Semantic Web paper [[SEMWEB01]]. Another key enabler is the recent progress in LLM-based agents that can follow instructions and use tools: just like previous generations of agents, LLM-based agents are designed for specific tasks, underscoring the need for open networks in which agents complement one another's abilities to solve more complex problems. New protocols and frameworks are emerging to support LLM-based agents to discover and use tools, or to discover and interact with other agents — many of them explicitly building on Web standards to foster interoperability (e.g., see the Model Context Protocol, Agent2Agent Protocol, Agent Network Protocol, Eclipse LMOS).
Conceptual Dimensions for Web-based Multi-Agent Systems
A multi-agent system (MAS) has several distinguishing features. One key feature is decentralized control, where each agent makes its own decisions and controls its own behavior — yet the MAS as a whole exhibits coordinated behavior to achieve system-level design objectives. Another key feature is that capabilities, knowledge, and resources are distributed among agents, which creates inter-dependencies: agents participate in a MAS because they need to interact with one another to solve problems that would otherwise exceed their individual capacities. Without such inter-dependencies, the MAS would be a collection of isolated agents — and would not constitute a system at all.
A non-trivial MAS therefore consists of more than just agents: for example, it may also include the tools that agents use to achieve their goals, the protocols through which they interact, and the policies or norms that govern their behavior. In research on Engineering MAS, these concerns have been organized along four conceptual dimensions [[DEMAZEAU95]]:
- Agent dimension: abstractions for designing and programming agents;
- Environment dimension: abstractions for designing and programming the shared environment;
- Interaction dimension: abstractions for specifying interactions among agents and potentially other entities;
- Organization dimension: abstractions for structuring and governing agent behavior.
These conceptual dimensions help organize the complexity of non-trivial MAS — and are particularly relevant when designing Web-based MAS [[HMAS]]: they offer a broader conceptual view of MAS (broader than just agents) while also defining the scope of the design space. For example, [[[#mas-web-transport-layer]]] shows a MAS modeled as agents that exchange messages. In this view, the Web is reduced to a message transport layer, an early perspective in research on Web-based MAS (see Section [[[#agents-web-services]]]). However, the Web was not designed as a transport layer (see Section 6.5.3 in [[FIELDING00]]).
In contrast, a broader conceptual view of MAS enables deeper integration with the Web: instead of limiting the Web to a transport layer for agent messages, it can leverage the Web as an application layer for MAS [[HMAS]]. For example, [[[#mas-web-application-layer]]] shows a MAS that incorporates concepts from all four dimensions mentioned above. In this view, the Web serves as the application layer for the agent environment — for example, providing agents with shared tools, resources, and governance mechanisms. This perspective expands the design space for Web-based MAS and aligns more closely with the Web's original purpose and capabilities.
State of Web-based Multi-Agent Systems
| Relevant Concepts | Agent Interaction | Tool Use | Identifiers | Descriptions | Discovery Mechanisms | Arch. Style | |
|---|---|---|---|---|---|---|---|
| MCP | Tool, Resource, Prompt | N/A | Function calling | Strings (Tools and Prompts),URIs (Resources) | Tool definition, Resource descriptions, Prompt definitions,(JSON) | Directories (via */list) | Client-Server with streaming RPC connectors (JSON-RPC 2.0, HTTP+SSE) |
| A2A | Agent Card, Task | Task invocation | N/A | Strings? | Agent Card, Task description,(JSON) | Well-known URIs,Directories | Async. Client-Server with streaming RPC connectors and webhooks (JSON-RPC 2.0, HTTP+SSE) |
| ANP | Agent,Agent Description,Communication Protocol | Communication protocols with protocol negotiation | N/A | W3C DID with custom Web-based Agent DID Method | Agent Description (RDF/JSON-LD) | Directories | Peer-to-Peer?(WebSocket subprotocol) |
| LMOS | Agent, Agent Group, Tool, Agent Description, Tool Description | Message passing?(in principle: TD interaction affordances) | Property Affordances,Event Affordances,Action Affordances(W3C WoT TD) | Uniform identifiers (IRIs, W3C DIDs) | Agent Description, Tool Description(W3C WoT TD; JSON, RDF/JSON-LD) | DNS-SD/mDNS,Well-known URIs,Directories(W3C WoT Discovery) | W3C WoT Arch.? with protocol bindings for HTTP and WebSocket subprotocol |
| FIPA | Agent,Agent Directory,Service Directory,Agent Communication Language,Interaction Protocol | FIPA Agent Communication Langauge,FIPA Agent Interaction Protocols | N/A | FIPA Agent Name | FIPA Agent Identifier Description | Directories | TODO |
| hMAS | Agent, Artifact, Agent Body, Workspace, Signifier, Role, Group, Organization, Resource Profile | Message passing,Signifiers for agent body affordances | Signifiers(W3C WoT TD, hMAS ontology) | Uniform identifiers (IRIs, W3C DIDs) | Resource Profile(W3C WoT TD or hMAS ontology; RDF/Turtle) | Hypermedia crawling,Search engines,Directories | Async. Client-Server with REST connectors (HTTP) and brokered pub/sub (W3C WebSub) |
| Multi-Agent MicroSevices (MAMS) | Agent, Agent Body, Resource, Microservices | FIPA ACL (over HTTP), REST, HTTP API, JMS | REST, HTTP API, JMS, W3C WOT TD | URIs (Agents, Agent Bodies, Resources) | Agent Bodies (JSON, JSON-LD (inc W3C WoT Hypermedia Controls Ontology), HAL) | Service Registries (Netflix Eureka), Link Crawling, Link Sharing | Microservices Architecture, Event Driven Architecture, REST |