CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Aimilios Hadjiliasi, Louis Nisiotis
• Venue: arXiv: cs.AI
• Published: 2026-08-10
• Collected: 2026-08-11
• URL: http://arxiv.org/abs/2608.09848v1
• PDF: https://arxiv.org/pdf/2608.09848v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The authors propose a modular cognitive architecture to develop Intelligent Virtual Agents (IVAs) that can operate in real-time interactive virtual environments. This architecture aims to bridge the gap between high-level reasoning models and real-time embodied execution for scalable, adaptive, and explainable agents.

What the Document Says

• The authors focus on developing cognitive IVAs in real-time interactive virtual environments.
• Existing architectures are either constrained by commercial game engines or difficult to implement in virtual worlds.
• The proposed architecture is modular and based on established frameworks like the Sense-Think-Act paradigm and Belief-Desire-Intention cognitive model.
• It aims to provide a reusable template for deploying IVA 'brains' in interactive 3D computing systems.

Key Concepts Mentioned

• Intelligent Virtual Agents (IVAs)
• Real-time interactive virtual environments
• Modular cognitive architecture
• Sense-Think-Act paradigm
• Belief-Desire-Intention cognitive model

Claims Made by the Document

• The development of IVAs in real-time interactive virtual environments is challenging.
• Existing architectures have limitations.
• The proposed architecture bridges the gap between high-level reasoning models and real-time embodied execution.

Evidence Used

• The authors' statements about the current challenges and their proposed solution.

Methods / Approach

• Developing a modular cognitive architecture based on established frameworks

Limitations Stated by the Authors

The paper does not discuss the specific limitations of the proposed architecture in detail.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The agent may face challenges in implementing and testing the proposed architecture due to lack of detailed information about its limitations.

Open Questions

• What are the specific limitations of the proposed architecture?
• How well does the proposed architecture perform compared to existing ones?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper focuses more on the concept and design of the architecture rather than its performance or comparison with other architectures.

Raw Abstract / Excerpt

The development of embodied Intelligent Virtual Agents (IVAs) that have cognitive capabilities in real-time interactive virtual environments remains a challenge, even with today's advancements in technology. Existing architectures are often focused on either the implementation of low-level reactive control systems that are constrained by commercial game engines, or high-level representations of reasoning models that can be difficult to implement in virtual worlds. This paper builds on that notion and proposes a modular cognitive architecture for deploying embodied IVAs. This architecture builds on existing, pre-established frameworks such as the Sense-Think-Act paradigm and the Belief-Desire-Intention cognitive model, among others, and aims to provide a reusable implementation-oriented framework as a template for deploying IVA 'brains' in interactive 3D computing systems. The proposed architecture contributes by providing a modular, implementation-oriented framework for the deployment of embodied, cognitive-capable IVAs and bridges the gap between high-level agent reasoning models with real-time embodied execution, for scalable, adaptive, and explainable agents in complex interactive virtual environments.