Cognitive Architectures for AI Agents

Overview

Cognitive architectures study how to organize an agent’s perception, memory, goals, reasoning, and actions so it can behave coherently over time. Approaches range from symbolic and BDI-style systems, state machines, and global-workspace models to LLM-based agents with memory, tools, reflection, and specialized components; many combine these methods with learning or embodied control. Researchers evaluate them on long-horizon tasks such as navigation, household and mobile-device control, tool use, multi-agent coordination, and robot deployment, while also examining safety and human oversight. A central challenge is making agents persistent, grounded, and reliable without sacrificing adaptability, efficiency, or interpretability; adding cognitive modules alone does not guarantee better performance.

Latest papers

CardsList

92 papers6 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

  1. HiVAE: Hierarchical Latent Variables for Scalable Theory of Mind

    Feb 18, 2026Nigel Doering, Rahath Malladi, Arshia Sangwan +2Theory of MindCognitive Architectures for AI Agents