Long-Lived Agents on the Web: Continuous Acquisition of Behaviors in Hypermedia Environments

Abstract

We demonstrate how autonomous goal-directed agents can exploit hypermedia to acquire and execute new behaviors at run time. In addition to behaviors programmed into the agents, in our system agents can discover and reuse behaviors extracted from machinereadable resource manuals. Such manuals can be published by developers, synthesized by agents through automated planning, or even specified by human users at run time. Agents can then discover and use physical and virtual resources in flexible ways, which allows them to better cope with the rapid evolution of open and dynamic Web environments. CCS CONCEPTS• Human-centered computing → Web-based interaction; Hypertext / hypermedia; • Computing methodologies → Multiagent systems.

Trustable service discovery for highly dynamic decentralized workflows

“…• Interfaces (APIs) to microservices are provisioned with service descriptions, in formats such as SPARQL [12], which offer self-describing mechanisms for interactions and exploit a capability for ''Continuous Acquisition of Behaviours'' [13]. RDF triples underlying SPARQL descriptions can be further augmented by service descriptions provided as Web of Things (WoT) 'Thing Descriptions' (TD) [14] or other JSON or JSON-LD [15] format Linked Data descriptions.…”

Enabling Discoverable Trusted Services for Highly Dynamic Decentralized Workflows

“…• Interfaces (APIs) to microservices are provisioned with SPARQL [5] service descriptions, which offer selfdescribing mechanisms for interactions, exploiting a capability for "Continuous Acquisition of Behaviors" [6], to make key features prominent, based on prior successful usage [7]. RDF triples underlying the SPARQL descriptions can be further augmented by service descriptions provided as Web of Things (WoT) 'Thing Descriptions' (TD) [8] or other JSON-LD [9] format Linked Data descriptions.…”