astra-langchain4j: Experiences Combining LLMs and Agent Programming

Given the emergence of Generative AI over the last two years and the increasing focus on Agentic AI as a form of Multi-Agent System it is important to explore both how such technologies can impact the use of traditional Agent Toolkits and how the wealth of experience encapsulated in those toolkits can influence the design of the new agentic platforms. This paper presents an overview of our experience developing a prototype large language model (LLM) integration for the ASTRA programming language. It presents a brief overview of the toolkit, followed by three example implementations, concluding with a discussion of the experiences garnered through the examples.

Towards Hypermedia Environments for Adaptive Coordination in Industrial Automation

Electromechanical systems manage physical processes through a network of inter-connected components. Today, programming the interactions required for coordinating these components is largely a manual process. This process is time-consuming and requires manual adaptation when system features change. To overcome this issue, we use autonomous software agents that process semantic descriptions of the system to determine coordination requirements and constraints; on this basis, they then interact with one another to control the system in a decentralized and coordinated manner.Our core insight is that coordination requirements between individual components are, ultimately, largely due to underlying physical interdependencies between the components, which can be (and, in many cases, already are) semantically modeled in automation projects. Agents then use hypermedia to discover, at run time, the plans and protocols required for enacting the coordination. A key novelty of our approach is the use of hypermedia-driven interaction: it reduces coupling in the system and enables its run-time adaptation as features change.

Signifiers as a First-class Abstraction in Hypermedia Multi-Agent Systems

Hypermedia APIs enable the design of reusable hypermedia clients that discover and exploit affordances on the Web. However, the reusability of such clients remains limited since they cannot plan and reason about interaction. This paper provides a conceptual bridge between hypermedia-driven affordance exploitation on the Web and methods for representing and reasoning about actions that have been extensively explored for Multi-Agent Systems (MAS) and, more broadly, Artificial Intelligence. We build on concepts and methods from Affordance Theory and Human-Computer Interaction that support interaction efficiency in open and evolvable environments to introduce signifiers as a first-class abstraction in Web-based MAS: Signifiers are designed with respect to the agent-environment context of their usage and enable agents with heterogeneous abilities to act and to reason about action. We define a formal model for the contextual exposure of signifiers in hypermedia environments that aims to drive affordance exploitation. We demonstrate our approach with a prototypical Web-based MAS where two agents with different reasoning abilities proactively discover how to interact with their environment by perceiving only the signifiers that fit their abilities. We show that signifier exposure can be inherently managed based on the dynamic agent-environment context towards facilitating effective and efficient interactions on the Web.