Cognitive Agent Programming Research Articles

The use of cognitive agent programs in management support

The use of cognitive agent programs in management support

Automating failure detection in cognitive agent programs

Debugging is notoriously difficult and time consuming but also essential for ensuring the reliability and quality of a software system. In order to reduce debugging effort and enable automated failure detection, we propose an automated testing framework for detecting failures in cognitive agent programs. Our approach is based on the assumption that modules within such programs are a natural unit for testing. We identify a minimal set of temporal operators that enable the specification of test conditions and show that the test language is sufficiently expressive for detecting all failure types of existing failure taxonomy. We also introduce an approach for specifying test templates that supports a programmer in writing tests. Furthermore, empirical analysis of agent programs allows us to evaluate whether our approach using test templates adequately detects failures, and to determine the effort that is required to do so in both single and multi-agent systems. We also discuss a concrete implementation of the proposed framework for the GOAL agent programming language that has been developed for the Eclipse IDE. With the use of this framework, evaluations have been performed based on test files and according questionnaires that were handed in by 94 novice programmers.

Automating failure detection in cognitive agent programs

Debugging is notoriously difficult and time consuming but also essential for ensuring the reliability and quality of a software system. In order to reduce debugging effort and enable automated failure detection, we propose an automated testing framework for detecting failures in cognitive agent programs. Our approach is based on the assumption that modules within such programs are a natural unit for testing. We identify a minimal set of temporal operators that enable the specification of test conditions and show that the test language is sufficiently expressive for detecting all failure types of existing failure taxonomy. We also introduce an approach for specifying test templates that supports a programmer in writing tests. Furthermore, empirical analysis of agent programs allows us to evaluate whether our approach using test templates adequately detects failures, and to determine the effort that is required to do so in both single and multi-agent systems. We also discuss a concrete implementation of the proposed framework for the GOAL agent programming language that has been developed for the Eclipse IDE. With the use of this framework, evaluations have been performed based on test files and according questionnaires that were handed in by 94 novice programmers.

Designing a source-level debugger for cognitive agent programs

When an agent program exhibits unexpected behaviour, a developer needs to locate the fault by debugging the agent’s source code. The process of fault localisation requires an understanding of how code relates to the observed agent behaviour. The main aim of this paper is to design a source-level debugger that supports single-step execution of a cognitive agent program. Cognitive agents execute a decision cycle in which they process events and derive a choice of action from their beliefs and goals. Current state-of-the-art debuggers for agent programs provide insight in how agent behaviour originates from this cycle but less so in how it relates to the program code. As relating source code to generated behaviour is an important part of the debugging task, arguably, a developer also needs to be able to suspend an agent program on code locations. We propose a design approach for single-step execution of agent programs that supports both code-based as well as cycle-based suspension of an agent program. This approach results in a concrete stepping diagram ready for implementation and is illustrated by a diagram for both the Goal and Jason agent programming languages, and a corresponding full implementation of a source-level debugger for Goal in the Eclipse development environment. The evaluation that was performed based on this implementation shows that agent programmers prefer a source-level debugger over a purely cycle-based debugger.

An empirical study of cognitive agent programs

Various agent programming languages and frameworks have been developed by now, but very few systematic studies have been done as to how the elements in these languages may be and are in fact used in practice. Performing a study of these aspects contr

Learning goal hierarchies from structured observations and expert annotations

We describe a relational learning by observation framework that automatically creates cognitive agent programs that model expert task performance in complex dynamic domains. Our framework uses observed behavior and goal annotations of an expert as the primary input, interprets them in the context of background knowledge, and returns an agent program that behaves similar to the expert. We map the problem of creating an agent program on to multiple learning problems that can be represented in a “supervised concept learning’’ setting. The acquired procedural knowledge is partitioned into a hierarchy of goals and represented with first order rules. Using an inductive logic programming (ILP) learning component allows our framework to naturally combine structured behavior observations, parametric and hierarchical goal annotations, and complex background knowledge. To deal with the large domains we consider, we have developed an efficient mechanism for storing and retrieving structured behavior data. We have tested our approach using artificially created examples and behavior observation traces generated by AI agents. We evaluate the learned rules by comparing them to hand-coded rules.