The paper proposes a minimal structural framework for cognitive representation and problem solving, emphasizing the role of context, invariance recognition, and representative selection. It introduces a Knowledge Space composed of a Concept Graph and a Procedure Graph to formalize these operations without relying on complex inference or learning mechanisms. Illustrative examples and a weak-solver demonstration show how proper representational organization can simplify problem solving and delineate success and failure conditions.
This paper asks how explicit representations can support reusable cognitive schemas in knowledge-based problem solving. We develop a structural framework in which schemas are organized by the informat...
arXiv:2606. 27721v1 Announce Type: new Abstract: Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both natural and artificial intelligence, and a key mechanism underlying chain-of-thought reasoning.
arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.
arXiv:2506. 20699v2 Announce Type: replace Abstract: Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization.
arXiv:2607. 09560v1 Announce Type: new Abstract: Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks.
The paper introduces CausalBridge, a framework that uses causal structure to assign semantics to unnamed variables in numerical measurements. By discovering a causal graph from the data and solving for variable embeddings constrained by this graph, the method aligns variable meanings with a language model, outperforming association‑based approaches. Experiments on questionnaires and robotics scenarios show high accuracy even when most variable names are masked, enabling rapid and cost‑effective system naming.
The paper argues that current AI systems are limited by their fixed representational frameworks and that true open‑ended intelligence requires the ability to extend its own semantic domain. By modeling cognitive states as partial evaluations over a formal language, the authors show that unresolved propositions create a frontier for extension that cannot be fully resolved by finite architectures. They propose that intelligence must transform unresolved structures into new spaces of meaning—generating new distinctions, questions, representations, and purposes—through persistent external memory and collective generative capacity.
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:2508. 11214v2 Announce Type: replace-cross Abstract: Explanations of cognitive behavior often appeal to computations over representations.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
The paper argues that for tasks whose behavior is tightly constrained by known structure—such as solvers, symmetry groups, or physical laws—finite data alone cannot fully capture the underlying mapping, even with expressive neural networks. It introduces the concept of a "structure gap," the performance difference between a method that incorporates this governing structure and a purely data‑driven learner. The authors prove this gap for a Gaussian inverse problem and provide additional theoretical bounds and experimental evidence in areas like sparse recovery and graph reachability.
ConceptARC at Scale introduces a generator that produces thousands of ARC-style tasks focused on specific spatial and semantic concepts, expanding the original benchmark by tenfold. The new dataset, ConceptARC-100, contains 1,600 manually reviewed tasks across 16 concepts, each with 100 tasks. Evaluation of large reasoning models on this dataset reveals that they reliably solve certain concepts, struggle with others, and develop internal representations that cluster by transformation operations such as recoloring, removal, or translation.