Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents
- URL: http://arxiv.org/abs/2311.13148v3
- Date: Wed, 3 Apr 2024 03:13:38 GMT
- Title: Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents
- Authors: Qinghua Lu, Liming Zhu, Xiwei Xu, Zhenchang Xing, Stefan Harrer, Jon Whittle,
- Abstract summary: Foundation model based agents derive their autonomy from the capabilities of foundation models.
This paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents.
- Score: 28.406492378232695
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation model based agents derive their autonomy from the capabilities of foundation models, which enable them to autonomously break down a given goal into a set of manageable tasks and orchestrate task execution to meet the goal. Despite the huge efforts put into building foundation model based agents, the architecture design of the agents has not yet been systematically explored. Also, while there are significant benefits of using agents for planning and execution, there are serious considerations regarding responsible AI related software quality attributes, such as security and accountability. Therefore, this paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents. We evaluate the completeness and utility of the proposed reference architecture by mapping it to the architecture of two real-world agents.
Related papers
- WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [85.95607119635102]
Large language models (LLMs) can mimic human-like intelligence.
WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents.
arXiv Detail & Related papers (2024-07-07T07:15:49Z) - Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents [22.94671478021277]
Foundation model-enabled generative artificial intelligence facilitates the development and implementation of agents.
We present a pattern catalogue consisting of 17 architectural patterns with analyses of the context, forces, and trade-offs.
arXiv Detail & Related papers (2024-05-16T23:24:48Z) - The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey [0.0]
This paper examines the recent advancements in AI agent implementations.
It focuses on their ability to achieve complex goals that require enhanced reasoning, planning, and tool execution capabilities.
arXiv Detail & Related papers (2024-04-17T17:32:41Z) - From Requirements to Architecture: An AI-Based Journey to
Semi-Automatically Generate Software Architectures [2.4150871564195007]
We propose a method to generate software architecture candidates based on requirements using artificial intelligence techniques.
We further envision an automatic evaluation and trade-off analysis of the generated architecture candidates.
arXiv Detail & Related papers (2024-01-25T10:56:58Z) - Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL)
This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
arXiv Detail & Related papers (2023-12-22T17:57:57Z) - Serving Deep Learning Model in Relational Databases [72.72372281808694]
Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains.
We highlight three pivotal paradigms: The state-of-the-artDL-Centric architecture offloadsDL computations to dedicated DL frameworks.
The potential UDF-Centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the database system.
The potentialRelation-Centric architecture aims to represent a large-scale tensor computation through operators.
arXiv Detail & Related papers (2023-10-07T06:01:35Z) - Conceptual Framework for Autonomous Cognitive Entities [0.9285295512807729]
This paper introduces the Autonomous Cognitive Entity model, a novel framework for a cognitive architecture.
The model is designed to harness the capabilities of the latest generative AI technologies, including large language models (LLMs) and multimodal generative models (MMMs)
The ACE framework also incorporates mechanisms for handling failures and adapting actions, thereby enhancing the robustness and flexibility of autonomous agents.
arXiv Detail & Related papers (2023-10-03T15:53:55Z) - A Reference Architecture for Designing Foundation Model based Systems [28.826700360670515]
There is a broad consensus that foundations models will be the fundamental building blocks for future AI systems.
incorporating foundations models into AI systems raises significant concerns about responsible and safe AI.
The paper proposes a pattern-oriented reference architecture for designing responsible foundation-model-based systems.
arXiv Detail & Related papers (2023-04-13T05:01:03Z) - Kernel Based Cognitive Architecture for Autonomous Agents [91.3755431537592]
This paper considers an evolutionary approach to creating a cognitive functionality.
We consider a cognitive architecture which ensures the evolution of the agent on the basis of Symbol Emergence Problem solution.
arXiv Detail & Related papers (2022-07-02T12:41:32Z) - Policy Architectures for Compositional Generalization in Control [71.61675703776628]
We introduce a framework for modeling entity-based compositional structure in tasks.
Our policies are flexible and can be trained end-to-end without requiring any action primitives.
arXiv Detail & Related papers (2022-03-10T06:44:24Z) - A Consciousness-Inspired Planning Agent for Model-Based Reinforcement
Learning [104.3643447579578]
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state.
The design allows agents to learn to plan effectively, by attending to the relevant objects, leading to better out-of-distribution generalization.
arXiv Detail & Related papers (2021-06-03T19:35:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.