English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs) have been widely recognised as transformativeartificial generative intelligence (AGI) technologies due to their capabilitiesto understand and generate content, including plans with reasoningcapabilities. Foundation model based agents derive their autonomy from thecapabilities of foundation models, which enable them to autonomously break downa given goal into a set of manageable tasks and orchestrate task execution tomeet the goal. Despite the huge efforts put into building foundation modelbased autonomous agents, the architecture design of the agents has not yet beensystematically explored. Also, while there are significant benefits of usingautonomous agents for planning and execution, there are serious considerationsregarding responsible AI related software quality attributes, such as securityand accountability. Therefore, this paper presents a pattern-oriented referencearchitecture that serves as architecture design guidance and enablesresponsible-AI-by-design when designing foundation model based autonomousagents. We evaluate the completeness and utility of the proposed referencearchitecture by mapping it to the architecture of two real-world agents.

Building the Future of Responsible AI: A Reference Architecture for Designing Large Language Model based Agents