Agent Communications Language

Agent Communication Language (ACL), are computer communication protocols that are intended for AI Agents to communication with each other.

During the 2007, protocols of this nature were proposed which include:

• FIPA-ACL^[1] (by the Foundation for Intelligent Physical Agents, a standardization consortium)
• KQML^[2] (Knowledge Query and Manipulation Language)

After the surge in Generative AI with the use of Transformers and Large language models, the definition of agent has shifted away from physical agents to signify software systems built using the principles of Agentic AI. A new protocol to emerge in this area is Natural Language Interaction Protocol (NLIP).^[3] NLIP is a standard being proposed by Ecma International, a standard body which focuses on application level standards in computer systems.

As a result, we can define agent communication protocols into two categories: Ontology based agent communication protocols and generative AI based agent communication protocols.

Ontology based agent communication protocols use a common ontology to be used between agents. An ontology is a part of the agent's knowledge base that describes what kind of things an agent can deal with and how they are related to each other. FIPA-ACL and KQML are examples of such protocols. These protocols rely on speech act theory developed by Searle in the 1960s^[4] and enhanced by Winograd and Flores in the 1970s. They define a set of performatives, also called Communicative Acts, and their meaning (e.g. ask-one). The content of the performative is not standardized, but varies from system to system. Implementation support of FIPA-ACL is included in FIPA-OS^[5][6] and Jade.^[7]

Generative AI based agent communication protocols such as NLIP^[8] do not require a shared ontology among communicating agents. In its stead, they use generative AI models to translate natural language text, images, videos or other modalities of data into a local ontology. This provides for hot-extensibility where the same protocol can be used for multiple communication needs, and simplifies version control since different agents can use different versions of a shared ontology. NLIP has been designed with security considerations in mind.^[9][10] The specification and standardization of NLIP is happening in Ecma Technical Community 56.^[11]