Conceptual Framework for Autonomous Cognitive Entities

arXiv 2310.06775 ↗First posted 3 Oct 2023cs.HC cs.AIcited by 6

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

The rapid development and adoption of Generative AI (GAI) technology in the form of chatbots such as ChatGPT and Claude has greatly increased interest in agentic machines. This paper introduces the Autonomous Cognitive Entity (ACE) model, a novel framework for a cognitive architecture, enabling machines and software agents to operate more independently. Drawing inspiration from the OSI model, the ACE framework presents layers of abstraction to conceptualize artificial cognitive architectures. The model is designed to harness the capabilities of the latest generative AI technologies, including large language models (LLMs) and multimodal generative models (MMMs), to build autonomous, agentic systems. The ACE framework comprises six layers: the Aspirational Layer, Global Strategy, Agent Model, Executive Function, Cognitive Control, and Task Prosecution. Each layer plays a distinct role, ranging from setting the moral compass and strategic thinking to task selection and execution. The ACE framework also incorporates mechanisms for handling failures and adapting actions, thereby enhancing the robustness and flexibility of autonomous agents. This paper introduces the conceptual framework and proposes implementation strategies that have been tested and observed in industry. The goal of this paper is to formalize this framework so as to be more accessible.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 45 of its 118 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

45 of 118 references.

Closest ancestors · 2

Same direction, newest first

Other references · 43

2022Large Language Models are Zero-Shot Reasonerscited by 4,323
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
2021On the Opportunities and Risks of Foundation Modelscited by 3,961
2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
2019An Introduction to Variational Autoencoderscited by 997
2020Meta-Learning in Neural Networks: A Surveycited by 944
2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389

31 more

2016Learning to reinforcement learncited by 369
2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 250
2023Large Language Model Guided Tree-of-Thoughtcited by 218
2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 140
2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 132
2023Taken out of context: On measuring situational awareness in LLMscited by 131
2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 111
2017AI Safety Gridworldscited by 108
2018Hierarchical Imitation and Reinforcement Learningcited by 88
2016Learning to Compose Neural Networks for Question Answeringcited by 85
2018Differentiable plasticity: training plastic neural networks with backpropagationcited by 83
2019Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researchcited by 58
2018Reasoning About Physical Interactions with Object-Oriented Prediction and Planningcited by 51
2023RETA-LLM: A Retrieval-Augmented Large Language Model Toolkitcited by 40
2017Cooperating with Machinescited by 39
2022Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Reviewcited by 37
2023Beyond Surface Statistics: Scene Representations in a Latent Diffusion Modelcited by 29
2016Distributed Constraint Optimization Problems and Applications: A Surveycited by 26
2023The Moral Machine Experiment on Large Language Modelscited by 24
2023Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Braincited by 18
2019A Survey of Distributed Consensus Protocols for Blockchain Networkscited by 16
2020AI virtues -- The missing link in putting AI ethics into practicecited by 9
2015Towards Verifiably Ethical Robot Behaviourcited by 7
2023Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structurescited by 7
2018The neural and cognitive architecture for learning from a small samplecited by 2
2022Who Reviews The Reviewers? A Multi-Level Jury Problemcited by 2
2021Service Oriented Architecture in Enterprise Applicationcited by 1
2022Eficiency of REST and gRPC realizing communication tasks in microservice-based ecosystemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

Similar, not cited

Close in wording, no citation either way