Enabling BDI Agents to Reason on a Dynamic Action Repertoire in Hypermedia Environments

Autonomy requires adaptability and persistence in pursuing long-term objectives within evolving contexts. While BDI agents can cope with dynamic and uncertain environments, their adaptability is typically constrained by static action repertoires, known a priori by designers. Through Semantic Web and Web of Things technologies, machine-readable action descriptions can be discovered in hypermedia environments, and updated dynamically to mirror the evolving landscape of actions offered by real-world environments. This paper proposes the integration of action-oriented BDI reasoning with signifiers that reveal information about action possibilities that may appear, disappear, or be modified in a hypermedia environment at any time. We extend the means-end reasoning of BDI agents with a mechanism for resolving signifiers discovered at run time into actions, which enables agents to adjust their decision-making based on action possibilities advertised in the environment. We evaluate our approach through experiments, where Jason agents discover signifiers expressed with available Web ontologies. The results demonstrate that our signifier resolution mechanism enhances action reasoning at run time towards effective goal achievement in dynamic and unknown environments.