AIBearisharXiv – CS AI · Jun 97/10
🧠A new academic paper challenges the capabilities of Large Language Models (LLMs) and chatbots in problem-solving conversations, arguing they cannot truly replicate human thinking or serve as genuine thinking partners. The research proposes that LLM training datasets encode artificial patterns rather than authentic human understanding, suggesting that even advanced AI development may not bridge this fundamental gap.
AINeutralarXiv – CS AI · Jun 27/10
🧠Researchers demonstrate that Transformers trained exclusively on adjacent comparisons spontaneously develop one-dimensional geometric structures that encode hidden rank orderings, exhibiting the symbolic distance effect observed in animal cognition. This discovery mechanistically bridges cognitive science with neural network representations, showing that decision confidence scales with ordinal distance even at ceiling accuracy.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce dual-trace memory encoding for LLM agents, pairing factual records with narrative scene reconstructions to improve cross-session recall by 20+ percentage points. The method significantly enhances temporal reasoning and multi-session knowledge aggregation without increasing computational costs, advancing the capability of persistent AI agent systems.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers propose a cognitive diagnostic framework that evaluates large language models across fine-grained ability dimensions rather than aggregate scores, enabling targeted model improvement and task-specific selection. The approach uses multidimensional Item Response Theory to estimate abilities across 35 dimensions for mathematics and generalizes to physics, chemistry, and computer science with strong predictive accuracy.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers introduce Zero-shot Visual World Models (ZWM), a computational framework inspired by how young children learn physical understanding from minimal data. The approach combines sparse prediction, causal inference, and compositional reasoning to achieve data-efficient learning, demonstrating that AI systems can match child development patterns while learning from single-child observational data.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers demonstrate that robots equipped with minimal embodied sensorimotor capabilities learn numerical concepts significantly faster than vision-only systems, achieving 96.8% counting accuracy with 10% of training data. The embodied neural network spontaneously develops biologically plausible number representations matching human cognitive development, suggesting embodiment acts as a structural learning prior rather than merely an information source.
AINeutralarXiv – CS AI · Apr 77/10
🧠Researchers found that large language models align with human brain activity during creative thinking tasks, with alignment increasing based on model size and idea originality. Different post-training approaches selectively reshape how LLMs align with creative versus analytical neural patterns in humans.
🧠 Llama
AIBearisharXiv – CS AI · Apr 77/10
🧠Research reveals that large language models like DeepSeek-V3.2, Gemini-3, and GPT-5.2 show rigid adaptation patterns when learning from changing environments, particularly struggling with loss-based learning compared to humans. The study found LLMs demonstrate asymmetric responses to positive versus negative feedback, with some models showing extreme perseveration after environmental changes.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · Mar 117/10
🧠Researchers propose a new theoretical framework called the 'Third Entity' to describe the emergent cognitive formation that arises from human-AI interactions, introducing the concept of 'vibe-creation' as a pre-reflective cognitive mode. The paper argues this represents the automation of tacit knowledge with significant implications for epistemology, education, and how we understand human-AI collaboration.
AIBearisharXiv – CS AI · Mar 56/10
🧠Research comparing four state-of-the-art language models (GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5, and Centaur) to humans in goal selection tasks reveals substantial divergence in behavior. While humans explore diverse approaches and learn gradually, the AI models tend to exploit single solutions or show poor performance, raising concerns about using current LLMs as proxies for human decision-making in critical applications.
🧠 Claude🧠 Gemini
AINeutralarXiv – CS AI · Mar 56/10
🧠Researchers introduce LifeBench, a new AI benchmark that tests long-term memory systems by requiring integration of both declarative and non-declarative memory across extended timeframes. Current state-of-the-art memory systems achieve only 55.2% accuracy on this challenging benchmark, highlighting significant gaps in AI's ability to handle complex, multi-source memory tasks.
AIBullisharXiv – CS AI · Mar 46/104
🧠Researchers analyzed Meta's NLLB-200 neural machine translation model across 135 languages, finding that it has implicitly learned universal conceptual structures and language genealogical relationships. The study reveals the model creates language-neutral conceptual representations similar to how multilingual brains organize information, with semantic relationships preserved across diverse languages.
AINeutralarXiv – CS AI · Mar 37/104
🧠Researchers propose the Compression Efficiency Principle (CEP) to explain why artificial neural networks and biological brains develop similar representations despite different substrates. The theory suggests both systems converge on efficient compression strategies that encode stable invariants rather than unstable correlations, providing a unified framework for understanding intelligence across biological and artificial systems.
AINeutralarXiv – CS AI · Jun 256/10
🧠Researchers test whether vision-language models exhibit human-like visual search behaviors using reasoning tokens as a proxy for cognitive effort. The study finds VLMs reproduce some human signatures—like increased effort in conjunction search—but diverge significantly in others, suggesting reasoning tokens offer a novel lens for understanding machine visual cognition.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce Ecologically Rational Meta-learned Inference (ERMI), a computational framework combining large language models with meta-learning to model human cognition as adaptive optimization to real-world environments. The approach successfully predicts human behavior across 15 experiments in function learning, category learning, and decision-making, suggesting human cognition reflects principled adaptation to ecological statistical structures.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers developed a hierarchical Adaptor Grammar (HAG) model that explains how humans learn abstract patterns from sequential experiences under cognitive constraints. The framework combines rate-distortion theory with program induction to show that learning order influences which abstractions are discovered, with experimental validation from melodic sequence learning tasks demonstrating superior generalization and fit compared to alternative models.
AINeutralarXiv – CS AI · Jun 235/10
🧠A new arXiv paper proposes a unified theoretical framework for understanding agency by grounding it in temporal organization, relational biology, and process ontology. The framework distinguishes between autonomy, goal-directedness, agency, and open-endedness through formalized timescale analysis, with implications for understanding biological systems, synthetic life, and artificial intelligence.
AINeutralarXiv – CS AI · Jun 236/10
🧠A multisite neurophysiological study reveals that AI-assisted programming fundamentally alters developers' cognitive processes differently than solo coding. Using EEG, eye-tracking, and biometric data, researchers found that AI assistance correlates with reduced cognitive engagement and changes how performance metrics align with physiological indicators, suggesting AI coding tools require distinct developer workflows and monitoring approaches.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers demonstrate that energy-based transformers, a class of neural networks linked to associative memory models, effectively predict reading difficulty across multiple eye-tracking and reading-time studies. The energy measure outperforms traditional metrics like surprisal and attention entropy, suggesting a unified approach to modeling human language processing.
AINeutralarXiv – CS AI · Jun 236/10
🧠A new academic paper argues that modern deep learning systems validate associationist theories of human learning, showing that supervised learning with evaluative feedback underlies diverse AI systems from language models to game-playing agents. While this vindicates classical associationist principles of uniform, gradual error-driven learning, the paper emphasizes that contemporary AI success depends on computational architectures far beyond what classical associationists imagined.
AINeutralarXiv – CS AI · Jun 125/10
🧠Researchers introduce Theory of Mind Utility (ToM-U), a formal computational framework for modeling how agents infer others' beliefs by tracking information access and credibility. The model uses directed graphs called Local Epistemic World Models to represent epistemic relationships and generates falsifiable predictions about mentalizing failures, advancing cognitive science theory beyond existing Bayesian and simulation-based approaches.
AI × CryptoBearishCrypto Briefing · Jun 116/10
🤖Jacob Ward discusses how AI systems subtly influence human decision-making through algorithmic manipulation, while examining how human brains distort reality perception. The commentary argues that addressing terrestrial challenges should take priority over space colonization ambitions, raising broader questions about technology ethics and resource allocation.
AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers introduce RAIL, a new evaluation framework for large audio-language models grounded in cognitive science principles rather than task-specific metrics. The benchmark, based on the Cattell-Horn-Carroll cognitive framework, reveals that state-of-the-art audio-language models exhibit uneven performance across core auditory cognitive abilities, highlighting a gap between how humans and current AI systems process audio information.
AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers introduce ATLAS, an active learning framework that automates scientific discovery by iteratively generating mechanistic hypotheses and designing optimal experiments to distinguish between them. Tested on reinforcement learning agents, ATLAS achieves 5-10x improvement in sample efficiency compared to random experimentation, demonstrating significant potential for accelerating human-interpretable insights in cognitive science and other mechanistic modeling domains.
AINeutralarXiv – CS AI · Jun 106/10
🧠This academic paper presents a geometric dynamical framework analyzing how predictive AI systems affect human cognitive exploration and problem-solving. The research suggests that early reliance on AI-generated solutions may constrain future exploratory capacity and delay recovery of independent cognitive flexibility, with implications for how assistance technologies are deployed in learning and decision-making contexts.
