astra-langchain4j: Experiences Combining LLMs and Agent Programming

2026-01-29

AI Summary

This work proposes a novel approach to address the challenges of integrating generative AI with agent-based systems by combining large language models (LLMs) with traditional agent programming paradigms. The study presents the first integration of LangChain4j and the ASTRA agent programming language, resulting in a hybrid multi-agent system that supports reasoning, communication, and collaboration. Guided by classical multi-agent theory, the design leverages established principles to structure LLM-driven agents, enhancing their behavioral coherence and predictability. The approach is validated through three representative application scenarios, demonstrating that conventional agent toolkits can significantly improve the structuredness and reliability of LLM-based agents. This synergy achieves bidirectional enhancement between traditional agent methodologies and emerging generative AI technologies.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

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.

Problem

• Generative AI
• Agentic AI
• Multi-Agent System
• Agent Toolkits
• LLM integration

Innovation

• LLM integration
• Agent Programming
• Agentic AI
• ASTRA
• Multi-Agent Systems