CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems
Summary
This paper proposes CEAA, a modular cognitive architecture for embodied intelligent virtual agents that integrates high-level reasoning models with real-time embodied execution in interactive 3D environments.
View Cached Full Text
Cached at: 08/11/26, 10:20 AM
Paper page - CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems
Source: https://huggingface.co/papers/2608.09848
Abstract
A modular cognitive architecture integrates high-level reasoning models with real-time embodied execution for scalable intelligent virtual agents in interactive 3D environments.
The development ofembodied 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 amodular cognitive architecturefor deploying embodied IVAs. This architecture builds on existing, pre-established frameworks such as theSense-Think-Act paradigmand the Belief-Desire-Intention cognitive model, among others, and aims to provide a reusable implementation-oriented framework as a template for deploying IVA “brains” ininteractive 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.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2608\.09848
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.09848 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.09848 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.09848 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI
Introduces a new paradigm called Combodied Agents that unify digital and embodied AI agents to model, predict, and support individual human-state trajectories over time, focusing on sustained human benefit rather than task completion.
Berkeley and Heiserman as an Unexhausted Architecture for Embodied Machine Intelligence
This paper argues that the machine intelligence architectures proposed by Edmund C. Berkeley and David L. Heiserman remain relevant for embodied robotic cognition, emphasizing logical states, hardware-near control, and modular sensorimotor structure.
Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction
This paper proposes Embodied-BenchClaw, an autonomous multi-agent system that automatically constructs embodied spatial intelligence benchmarks from user intent through a five-stage pipeline with process quality control and an extensible Skill Library.
Physically Viable World Models: A Case for Query-Conditioned Embodied AI
This paper argues that world models for embodied AI must be physically viable and query-conditioned, focusing on identifying the simplest physical abstraction for each intervention query rather than merely predicting observations.
@h100envy: This paper completely changed how I think about an autonomous engineer agent: Give the agent an interface, not bash -> …
This paper introduces an Agent-Computer Interface (ACI) for autonomous coding agents, replacing raw bash with purpose-built commands for navigation, editing, and feedback, achieving state-of-the-art results on SWE-bench and HumanEvalFix.