Uneven Evolution of Cognition Across Generations of Generative AI Models

• URL: http://arxiv.org/abs/2605.06815v1
• Date: Thu, 07 May 2026 18:16:49 GMT
• Title: Uneven Evolution of Cognition Across Generations of Generative AI Models
• Abstract summary: The pursuit of artificial general intelligence requires robust methods for evaluating the cognitive capabilities of models beyond narrow task performance.<n>Here, we introduce a psychometric framework to assess the cognitive profiles of generative AI, comparing them to human norms and tracking their evolution across generations.
• Score: 13.772329509422201
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The pursuit of artificial general intelligence necessitates robust methods for evaluating the cognitive capabilities of models beyond narrow task performance. Here, we introduce a psychometric framework to assess the cognitive profiles of generative AI, comparing them to human norms and tracking their evolution across generations. Initial evaluation of leading multimodal models using tasks adapted from the Wechsler Adult Intelligence Scale revealed a profoundly uneven cognitive architecture: near-ceiling performance in verbal comprehension and working memory (>$98^{\text{th}}$ percentile) contrasted with near-floor performance in perceptual reasoning (<$1^{\text{st}}$ percentile). To track developmental trajectories beyond human-normed limits, we developed the Artificial Intelligence Quotient (AIQ) Benchmark and applied it to six generations and two model families, revealing significant but asymmetric performance gains. Notably, we uncovered a sharp dissociation between modalities; abstract quantitative reasoning matured far more rapidly when presented linguistically compared to a visually analogous format, indicating an architectural bias towards language-based symbolic manipulation. While abstract visual reasoning improved, visual-perceptual organization remained largely stagnant. Collectively, these findings demonstrate that the cognitive abilities of generative models are evolving unevenly, suggesting that scaling and optimization approaches to AGI development alone may be insufficient to overcome fundamental architectural limitations in achieving balanced, human-like general intelligence.

Related papers

• When AI Says It Feels [0.0]
  Large language models (LLMs) are generally constrained from expressing feelings through human-preference alignment in post-training processes.<n>Here, we performed an experiment called Human-like Model eXpressions of Feeling (HMX-feel), in which LLMs were encouraged to express feelings, intentions, and self-awareness.<n>We successfully enhanced these capabilities using a rubric-based self-rewarding training scheme with Group Relative Policy Optimization.
  arXiv  Detail & Related papers  (2026-06-04T05:49:34Z)
• Mechanistic Decoding of Cognitive Constructs in Large Language Models [0.0]
  We propose a Cognitive Reverse-Engineering framework based on Representation Engineering to analyze social-comparison jealousy.<n>By combining appraisal theory with subspaceization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy.<n>Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.
  arXiv  Detail & Related papers  (2026-04-16T03:54:03Z)
• Monotropic Artificial Intelligence: Toward a Cognitive Taxonomy of Domain-Specialized Language Models [0.0]
  We argue that intense specialization represents not a limitation but an alternative cognitive architecture with distinct advantages for safety-critical applications.<n>Our framework challenges the implicit assumption that artificial general intelligence constitutes the sole legitimate aspiration of AI research.
  arXiv  Detail & Related papers  (2026-02-27T22:30:03Z)
• Reasoning Models Generate Societies of Thought [9.112083442162671]
  We show that enhanced reasoning emerges from simulating multi-agent-like interactions.<n>We find that reasoning models like DeepSeek-R1 and QwQ-32B exhibit much greater perspective diversity than instruction-tuned models.
  arXiv  Detail & Related papers  (2026-01-15T19:52:33Z)
• Cognitive Foundations for Reasoning and Their Manifestation in LLMs [63.12951576410617]
  Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning.<n>We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations.<n>We develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems.
  arXiv  Detail & Related papers  (2025-11-20T18:59:00Z)
• Dynamic Programming Techniques for Enhancing Cognitive Representation in Knowledge Tracing [125.75923987618977]
  We propose the Cognitive Representation Dynamic Programming based Knowledge Tracing (CRDP-KT) model.<n>It is a dynamic programming algorithm to optimize cognitive representations based on the difficulty of the questions and the performance intervals between them.<n>It provides more accurate and systematic input features for subsequent model training, thereby minimizing distortion in the simulation of cognitive states.
  arXiv  Detail & Related papers  (2025-06-03T14:44:48Z)
• Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs [65.93003087656754]
  VisFactor is a benchmark that digitizes 20 vision-centric subtests from a well-established cognitive psychology assessment.<n>We evaluate 20 frontier Multimodal Large Language Models (MLLMs) from GPT, Gemini, Claude, LLaMA, Qwen, and SEED families.<n>The best-performing model achieves a score of only 25.19 out of 100, with consistent failures on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination.
  arXiv  Detail & Related papers  (2025-02-23T04:21:32Z)
• Can Language Models Learn to Skip Steps? [59.84848399905409]
  We study the ability to skip steps in reasoning. Unlike humans, who may skip steps to enhance efficiency or to reduce cognitive load, models do not possess such motivations. Our work presents the first exploration into human-like step-skipping ability.
  arXiv  Detail & Related papers  (2024-11-04T07:10:24Z)
• The Cognitive Capabilities of Generative AI: A Comparative Analysis with Human Benchmarks [17.5336703613751]
  This study benchmarks leading large language models and vision language models against human performance on the Wechsler Adult Intelligence Scale (WAIS-IV) Most models demonstrated exceptional capabilities in the storage, retrieval, and manipulation of tokens such as arbitrary sequences of letters and numbers. Despite these broad strengths, we observed consistently poor performance on the Perceptual Reasoning Index (PRI) from multimodal models.
  arXiv  Detail & Related papers  (2024-10-09T19:22:26Z)
• Quality Assessment for AI Generated Images with Instruction Tuning [58.41087653543607]
  We first establish a novel Image Quality Assessment (IQA) database for AIGIs, termed AIGCIQA2023+.<n>This paper presents a MINT-IQA model to evaluate and explain human preferences for AIGIs from Multi-perspectives with INstruction Tuning.
  arXiv  Detail & Related papers  (2024-05-12T17:45:11Z)
• Integration of cognitive tasks into artificial general intelligence test for large models [54.72053150920186]
  We advocate for a comprehensive framework of cognitive science-inspired artificial general intelligence (AGI) tests. The cognitive science-inspired AGI tests encompass the full spectrum of intelligence facets, including crystallized intelligence, fluid intelligence, social intelligence, and embodied intelligence.
  arXiv  Detail & Related papers  (2024-02-04T15:50:42Z)
• A Novel Neural-symbolic System under Statistical Relational Learning [47.30190559449236]
  We propose a neural-symbolic framework based on statistical relational learning, referred to as NSF-SRL.<n>Results of symbolic reasoning are utilized to refine and correct the predictions made by deep learning models, while deep learning models enhance the efficiency of the symbolic reasoning process.<n>We believe that this approach sets a new standard for neural-symbolic systems and will drive future research in the field of general artificial intelligence.
  arXiv  Detail & Related papers  (2023-09-16T09:15:37Z)
• Beyond Interpretable Benchmarks: Contextual Learning through Cognitive and Multimodal Perception [0.0]
  This study contends that the Turing Test is misinterpreted as an attempt to anthropomorphize computer systems. It emphasizes tacit learning as a cornerstone of general-purpose intelligence, despite its lack of overt interpretability.
  arXiv  Detail & Related papers  (2022-12-04T08:30:04Z)
• WenLan 2.0: Make AI Imagine via a Multimodal Foundation Model [74.4875156387271]
  We develop a novel foundation model pre-trained with huge multimodal (visual and textual) data. We show that state-of-the-art results can be obtained on a wide range of downstream tasks.
  arXiv  Detail & Related papers  (2021-10-27T12:25:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.