Advances in Cognitive Architectures and Epistemology

The field of artificial intelligence is shifting towards a more nuanced understanding of intelligence, with a focus on epistemology and cognitive architectures. Researchers are moving away from solely data-driven approaches and instead exploring the role of theory and error-centric intelligence in achieving true cognitive abilities. This is evident in the development of new frameworks and models that prioritize intentional understanding, executable epistemology, and the integration of cognitive and affective processes. Notable papers in this area include: Executable Epistemology, which introduces the Structured Cognitive Loop as an executable epistemological framework for emergent intelligence. Towards Error Centric Intelligence, which challenges the Platonic Representation Hypothesis and proposes Causal Mechanics as a mechanisms-first program for error discovery and correction.

Sources

Towards Error Centric Intelligence I, Beyond Observational Learning

Visualizing miniKanren Search with a Fine-Grained Small-Step Semantics

From Murals to Memes: A Theory of Aesthetic Asymmetry in Political Mobilization

Executable Epistemology: The Structured Cognitive Loop as an Architecture of Intentional Understanding

PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency

Limits of Emergent Reasoning of Large Language Models in Agentic Frameworks for Deterministic Games

SimpliPy: A Source-Tracking Notional Machine for Simplified Python

Learning Ecology with VERA Using Conceptual Models and Simulations

Toward a Cognitive-Affective-Systemic Framework for Art and Sustainability

Complexity of Unambiguous Problems in $\Sigma^P_2$

Knowledge and Common Knowledge of Strategies

Built with on top of