arXiv:2608. 06839v1 Announce Type: new Abstract: Artificial Neural networks (ANNs) are often treated as black-box models, making explainability a central challenge in deep learning.
arXiv:2512. 09831v2 Announce Type: replace Abstract: This paper develops a geometric framework for modeling concepts, motivation, and influence across cognitively heterogeneous agents.
arXiv:2608.29530v1 Announce Type: cross Abstract: Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modele...
arXiv:2605. 22093v3 Announce Type: replace Abstract: Knowledge graphs have become the primary vehicle for data integration and are critical to the success of modern AI, but the diversity of KG modelling practices, from lightweight vocabularies to richly axiomatised ontologies, makes integration and reuse expensive and brittle.
The paper argues that human cognitive constraints, often seen as limits, actually drive mathematical progress by creating bottlenecks that force the development of new abstractions. It proposes a resource‑rational theory of mathematical abstraction, showing how these bottlenecks can lead to novel formalisms with broader applications. The authors illustrate this with historical examples and suggest that incorporating similar constraints into machine learning could aid in discovering useful mathematical abstractions.
The article discusses goals as cognitive states that combine with world knowledge to guide purposeful behavior, emphasizing their compositional nature and relation to rational action. It draws parallels between goal representations and the syntax‑semantics interface in linguistics and logic, highlighting questions about expressivity, design, and efficiency of different goal languages. The authors synthesize research on goal representation properties, propose a broader design space, and suggest that distinguishing form and meaning can clarify assumptions, inform cognition‑motivation interactions, and identify variation axes in goal conceptions.
arXiv:2607. 05168v1 Announce Type: new Abstract: Why do intelligent systems need to perform explicit symbolic reasoning?
arXiv:2608. 08443v1 Announce Type: cross Abstract: Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a relational microculture.
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
The paper investigates whether current reasoning models exhibit systematicity—the idea that understanding one concept should extend to closely related variations—by extending rule induction tasks from cognitive science. Using task isomorphisms like recombination and substitution, the authors generate structurally equivalent task variants and test models on them. Results show that while models can solve the original tasks, they frequently fail on these equivalent variants, indicating a lack of systematicity in their reasoning abilities.
arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.
arXiv:2509. 14474v3 Announce Type: replace Abstract: The debate around Artificial General Intelligence (AGI) remains open due to two fundamentally different goals: replicating human-level performance versus replicating human-like cognitive processes.