A simple language for generic dialogues: "Speech acts" for communication

The paper presents the preliminary results of an experimental project for a new agent communication language. The applicative research context suggesting such an aim is the one traditionally identified by the Artificial Intelligence in Education community: this context, as it is motivated in the paper, is generic enough to represent a wider class of applications, i.e. all those that privilege communication among autonomous (open) human and artificial agents. In order to satisfy the needs and constraints of the applicative context a first model/architecture, called STROBE, has been designed and a prototype has been implemented. STROBE is supposed to become the kernel of the new language and of its applications. The main property of STROBE is that its description language coincides with its implementation language, i.e. Scheme. Basically, STROBE shows how generic communication may be described and implemented by means of STReams of pragmatically marked messages to be exchanged by agents represented as OBjects interpreting messages in multiple Environments. Recent advancements in the project are producing new modules to be integrated in the STROBE architecture, in particular: a re-implementation of the language for software agents KQML: Knowledge Query and Manipulation Language for allowing a richer set of performatives to enhance the original pragmatic markers. This integration is the main issue discussed in the paper. Other steps, such as a multitasking operating system to manage multiple communication, a Scheme-based Simple Reflective Interpreter in Continuation Passing Style to allow meta-reasoning, and a Scheme interpreter in Java to integrate higher level descriptions with lower level interface and networking functionalities, in a platform-independent fashion, are indicated as ongoing developments. An outline of the expected functionalities of the language under development may allow to appreciate if and how it may fit the expected ones, i.e. cognitive simplicity for designing and controlling multi-agent generic dialogues, including human and artificial communication facilities.