Internal World Models as Imagination Networks in Cognitive Agents

• URL: http://arxiv.org/abs/2510.04391v2
• Date: Thu, 06 Nov 2025 19:24:28 GMT
• Title: Internal World Models as Imagination Networks in Cognitive Agents
• Authors: Saurabh Ranjan, Brian Odegaard,
• Abstract summary: We propose that imagination serves to access an internal world model (IWM) and use psychological network analysis to explore IWMs in humans and large language models (LLMs)<n>Our study offers a novel method for comparing internally-generated representations in humans and AI, providing insights for developing human-like imagination in artificial intelligence.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: What is the computational objective of imagination? While classical interpretations suggest imagination is useful for maximizing rewards, recent findings challenge this view. In this study, we propose that imagination serves to access an internal world model (IWM) and use psychological network analysis to explore IWMs in humans and large language models (LLMs). Specifically, we assessed imagination vividness ratings using two questionnaires and constructed imagination networks from these reports. Imagination networks from human groups showed correlations between different centrality measures, including expected influence, strength, and closeness. However, imagination networks from LLMs showed a lack of clustering and lower correlations between centrality measures under different prompts and conversational memory conditions. Together, these results indicate a lack of similarity between IWMs in human and LLM agents. Overall, our study offers a novel method for comparing internally-generated representations in humans and AI, providing insights for developing human-like imagination in artificial intelligence.

Related papers

• Learning Situated Awareness in the Real World [63.75211123289058]
  SAW-Bench is a novel benchmark for evaluating egocentric situated awareness using real-world videos.<n>It probes a model's observer-centric understanding with six different awareness tasks.<n>Our comprehensive evaluation reveals a human-model performance gap of 37.66%, even with the best-performing MFM, Gemini 3 Flash.
  arXiv  Detail & Related papers  (2026-02-18T18:22:52Z)
• When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning [108.73849507002195]
  We present an in-depth analysis of test-time visual imagination as a controllable resource for spatial reasoning.<n>We study when static visual evidence is sufficient, when imagination improves reasoning, and how excessive or unnecessary imagination affects accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-02-09T03:21:48Z)
• Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models [60.543714835980325]
  Humans construct internal world models and reason by manipulating the concepts within these models.<n>Recent advances in AI approximate such human cognitive abilities, where world models are believed to be embedded within large language models.<n>This paper presents the first principled study of when and how visual generation benefits reasoning.
  arXiv  Detail & Related papers  (2026-01-27T17:40:07Z)
• Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports [18.336392633341493]
  We show that large-scale similarity judgments can more faithfully capture the brain's affective geometry.<n>Our findings provide compelling evidence that MLLMs can autonomously develop rich, neurally-aligned affective representations.
  arXiv  Detail & Related papers  (2025-09-29T05:22:33Z)
• Don't Forget Imagination! [0.0]
  This paper is a call for greater attention to cognitive imagination as the next promising breakthrough in artificial intelligence.<n>We propose semantic models -- a new approach to mathematical models that can learn, like neural networks, and are based on probabilistic causal relationships.
  arXiv  Detail & Related papers  (2025-08-08T06:50:43Z)
• Embodied AI Agents: Modeling the World [188.85697524284834]
  This paper describes our research on AI agents embodied in visual, virtual or physical forms.<n>We propose that the development of world models is central to reasoning and planning of embodied AI agents.<n>We also propose to learn the mental world model of users to enable better human-agent collaboration.
  arXiv  Detail & Related papers  (2025-06-27T16:05:34Z)
• How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition [75.11808682808065]
  This study investigates whether large language models (LLMs) exhibit similar tendencies in understanding semantic size.<n>Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding.<n> Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario.
  arXiv  Detail & Related papers  (2025-03-01T03:35:56Z)
• Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models [2.9312156642007294]
  We systematically review Large Language Models' capabilities across three important cognitive domains: decision-making biases, reasoning, and creativity.<n>On decision-making, our synthesis reveals that while LLMs demonstrate several human-like biases, some biases observed in humans are absent.<n>On reasoning, advanced LLMs like GPT-4 exhibit deliberative reasoning akin to human System-2 thinking, while smaller models fall short of human-level performance.<n>A distinct dichotomy emerges in creativity: while LLMs excel in language-based creative tasks, such as storytelling, they struggle with divergent thinking tasks that require real-world context.
  arXiv  Detail & Related papers  (2024-12-20T02:26:56Z)
• Alien Recombination: Exploring Concept Blends Beyond Human Cognitive Availability in Visual Art [90.8684263806649]
  We show how AI can transcend human cognitive limitations in visual art creation. Our research hypothesizes that visual art contains a vast unexplored space of conceptual combinations. We present the Alien Recombination method to identify and generate concept combinations that lie beyond human cognitive availability.
  arXiv  Detail & Related papers  (2024-11-18T11:55:38Z)
• Semiotics Networks Representing Perceptual Inference [0.0]
  We present a computational model designed to track and simulate the perception of objects.<n>Our model is not limited to persons and can be applied to any system featuring a loop involving the processing from "internal" to "external" representations.
  arXiv  Detail & Related papers  (2023-10-08T16:05:17Z)
• Grounding Psychological Shape Space in Convolutional Neural Networks [0.0]
  We use convolutional neural networks to learn a generalizable mapping between perceptual inputs and a recently proposed psychological similarity space for the shape domain. Our results indicate that a classification-based multi-task learning scenario yields the best results, but that its performance is relatively sensitive to the dimensionality of the similarity space.
  arXiv  Detail & Related papers  (2021-11-16T12:21:07Z)
• 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.