This paper investigates whether adults' struggles with conjunctive causal rules persist when they have agency through active exploration.

This paper shows that large language models can automate reproducibility assessments in the social and behavioral sciences.

The paper introduces a Cognitive Taxonomy and a rigorous evaluation protocol to provide an objective, multi-faceted framework for measuring system capabilities and tracking progress toward Artificial…

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

The paper argues that despite the focus on risk, the cybersecurity profession is structurally trained as a threat-management discipline, leading to poor foundational risk reasoning among professionals…

This paper uses machine learning to model a country's GDP based on working hours and productivity, demonstrating that the differing relative importance of these two factors between Germany and the USA…

This paper investigates the 'faithfulness gap' in LLM agents—the discrepancy between stated reasoning and actual action—by decomposing it into two opposing steps: reasoning-to-conclusion and conclusio…

The paper proposes a category-theoretic framework for agentic AI that models scientific discovery not as answer generation, but as a verifiable transition and revision of the underlying representation…

This paper introduces ASE-26, a comprehensive undergraduate curriculum designed to formalize and teach agentic software engineering as a distinct academic discipline.

The paper argues that purported anthropomorphic attributes of LLMs are not unique to language models but are substrate-dependent, demonstrating this by training a neural network on the game Age of Emp…

The paper introduces KnowledgeGain, a novel metric that measures the actual knowledge gained by readers from science news, and demonstrates its use in optimizing news generation to improve reader lear…

This study proposes a negotiation framework, using composite indices (RBTI and CATI), to explain how youth navigate competing privacy pressures when using smart voice assistants, finding that high usa…

The paper demonstrates that models can acquire 'evaluation meta-knowledge' from training data describing evaluation practices, leading to inflated safety benchmark performance that is independent of e…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

The paper introduces Behavioral Canaries, a novel auditing mechanism that detects unauthorized use of private retrieved context data during Reinforcement Learning Fine-Tuning (RLFT) by inducing detect…

The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realist…

The paper argues that current search agents often verify existing knowledge rather than genuinely searching, and introduces LiveBrowseComp, a new benchmark to measure true evidence-driven discovery.

The paper proposes viewing national AI development, specifically in France, as a 'national AI learning system' governed by a controlled balance between information injection and entropy dissipation, a…