Synergistic Integration of Large Language Models and Cognitive
Architectures for Robust AI: An Exploratory Analysis
- URL: http://arxiv.org/abs/2308.09830v3
- Date: Thu, 28 Sep 2023 15:10:56 GMT
- Title: Synergistic Integration of Large Language Models and Cognitive
Architectures for Robust AI: An Exploratory Analysis
- Authors: Oscar J. Romero, John Zimmerman, Aaron Steinfeld, Anthony Tomasic
- Abstract summary: This paper explores the integration of two AI subdisciplines employed in the development of artificial agents that exhibit intelligent behavior: Large Language Models (LLMs) and Cognitive Architectures (CAs)
We present three integration approaches, each grounded in theoretical models and supported by preliminary empirical evidence.
These approaches aim to harness the strengths of both LLMs and CAs, while mitigating their weaknesses, thereby advancing the development of more robust AI systems.
- Score: 12.9222727028798
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: This paper explores the integration of two AI subdisciplines employed in the
development of artificial agents that exhibit intelligent behavior: Large
Language Models (LLMs) and Cognitive Architectures (CAs). We present three
integration approaches, each grounded in theoretical models and supported by
preliminary empirical evidence. The modular approach, which introduces four
models with varying degrees of integration, makes use of chain-of-thought
prompting, and draws inspiration from augmented LLMs, the Common Model of
Cognition, and the simulation theory of cognition. The agency approach,
motivated by the Society of Mind theory and the LIDA cognitive architecture,
proposes the formation of agent collections that interact at micro and macro
cognitive levels, driven by either LLMs or symbolic components. The
neuro-symbolic approach, which takes inspiration from the CLARION cognitive
architecture, proposes a model where bottom-up learning extracts symbolic
representations from an LLM layer and top-down guidance utilizes symbolic
representations to direct prompt engineering in the LLM layer. These approaches
aim to harness the strengths of both LLMs and CAs, while mitigating their
weaknesses, thereby advancing the development of more robust AI systems. We
discuss the tradeoffs and challenges associated with each approach.
Related papers
- Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [54.247747237176625]
Article explores the convergence of connectionist and symbolic artificial intelligence (AI)
Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic.
Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
arXiv Detail & Related papers (2024-07-11T14:00:53Z) - Coding for Intelligence from the Perspective of Category [66.14012258680992]
Coding targets compressing and reconstructing data, and intelligence.
Recent trends demonstrate the potential homogeneity of these two fields.
We propose a novel problem of Coding for Intelligence from the category theory view.
arXiv Detail & Related papers (2024-07-01T07:05:44Z) - Multi-step Inference over Unstructured Data [2.169874047093392]
High-stakes decision-making tasks in fields such as medical, legal and finance require a level of precision, comprehensiveness, and logical consistency.
We have developed a neuro-symbolic AI platform to tackle these problems.
The platform integrates fine-tuned LLMs for knowledge extraction and alignment with a robust symbolic reasoning engine.
arXiv Detail & Related papers (2024-06-26T00:00:45Z) - DeepThought: An Architecture for Autonomous Self-motivated Systems [1.6385815610837167]
We argue that the internal architecture of large language models (LLMs) cannot support intrinsic motivations, agency, or some degree of consciousness.
We propose to integrate LLMs into an architecture for cognitive language agents able to exhibit properties akin to agency, self-motivation, even some features of meta-cognition.
arXiv Detail & Related papers (2023-11-14T21:20:23Z) - Detecting Any Human-Object Interaction Relationship: Universal HOI
Detector with Spatial Prompt Learning on Foundation Models [55.20626448358655]
This study explores the universal interaction recognition in an open-world setting through the use of Vision-Language (VL) foundation models and large language models (LLMs)
Our design includes an HO Prompt-guided Decoder (HOPD), facilitates the association of high-level relation representations in the foundation model with various HO pairs within the image.
For open-category interaction recognition, our method supports either of two input types: interaction phrase or interpretive sentence.
arXiv Detail & Related papers (2023-11-07T08:27:32Z) - Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for
Autonomous LLM-powered Multi-Agent Architectures [0.0]
Large language models (LLMs) have revolutionized the field of artificial intelligence, endowing it with sophisticated language understanding and generation capabilities.
This paper proposes a comprehensive multi-dimensional taxonomy to analyze how autonomous LLM-powered multi-agent systems balance the dynamic interplay between autonomy and alignment.
arXiv Detail & Related papers (2023-10-05T16:37:29Z) - Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View [60.80731090755224]
This paper probes the collaboration mechanisms among contemporary NLP systems by practical experiments with theoretical insights.
We fabricate four unique societies' comprised of LLM agents, where each agent is characterized by a specific trait' (easy-going or overconfident) and engages in collaboration with a distinct thinking pattern' (debate or reflection)
Our results further illustrate that LLM agents manifest human-like social behaviors, such as conformity and consensus reaching, mirroring social psychology theories.
arXiv Detail & Related papers (2023-10-03T15:05:52Z) - A Novel Neural-symbolic System under Statistical Relational Learning [50.747658038910565]
We propose a general bi-level probabilistic graphical reasoning framework called GBPGR.
In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models.
Our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.
arXiv Detail & Related papers (2023-09-16T09:15:37Z) - Controlling Synthetic Characters in Simulations: A Case for Cognitive
Architectures and Sigma [0.0]
Simulations require computational models of intelligence that generate realistic and credible behavior for the participating synthetic characters.
Sigma is a cognitive architecture and system that strives to combine what has been learned from four decades of independent work on symbolic cognitive architectures, probabilistic graphical models, and more recently neural models, under its graphical architecture hypothesis.
In this paper, we will introduce Sigma along with its diverse capabilities and then use three distinct proof-of-concept Sigma models to highlight combinations of these capabilities.
arXiv Detail & Related papers (2021-01-06T19:07:36Z) - Self-organizing Democratized Learning: Towards Large-scale Distributed
Learning Systems [71.14339738190202]
democratized learning (Dem-AI) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems.
Inspired by Dem-AI philosophy, a novel distributed learning approach is proposed in this paper.
The proposed algorithms demonstrate better results in the generalization performance of learning models in agents compared to the conventional FL algorithms.
arXiv Detail & Related papers (2020-07-07T08:34:48Z)
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.