Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs) in natural language processing have sparked discussions regarding whether these models possess capability of curiosity-driven learning akin to humans. In this paper, starting from the human curiosity assessment questionnaire Five-Dimensional Curiosity scale Revised (5DCR), we design a comprehensive evaluation framework that covers dimensions such as Information Seeking, Thrill Seeking, and Social Curiosity to assess the extent of curiosity exhibited by LLMs. The results demonstrate that LLMs exhibit a stronger thirst for knowledge than humans but still tend to make conservative choices when faced with uncertain environments. We further investigated the relationship between curiosity and thinking of LLMs, confirming that curious behaviors can enhance the model's reasoning and active learning abilities. These findings suggest that LLMs have the potential to exhibit curiosity similar to that of humans, providing experimental support for the future development of learning capabilities and innovative research in LLMs.
This book discusses computational curiosity, from the psychology of curiosity to the computational models of curiosity, and then showcases several interesting applications of computational curiosity. A brief overview of the book is given as follows. Chapter 1 discusses the underpinnings of curiosity in human beings, including the major categories of curiosity, curiosity-related emotions and behaviors, and the benefits of curiosity. Chapter 2 reviews the arousal theories of curiosity in psychology and summarizes a general two-step process model for computational curiosity. Base on the perspective of the two-step process model, Chapter 3 reviews and analyzes some of the traditional computational models of curiosity. Chapter 4 introduces a novel generic computational model of curiosity, which is developed based on the arousal theories of curiosity. After the discussion of computational models of curiosity, we outline the important applications where computational curiosity may bring significant impacts in Chapter 5. Chapter 6 discusses the application of the generic computational model of curiosity in a machine learning framework. Chapter 7 discusses the application of the generic com
Recent advances in Large Language Models (LLMs) have expanded their role in human interaction, yet curiosity -- a central driver of inquiry -- remains underexplored in these systems, particularly across cultural contexts. In this work, we investigate cultural variation in curiosity using Yahoo! Answers, a real-world multi-country dataset spanning diverse topics. We introduce CUEST (CUriosity Evaluation across SocieTies), an evaluation framework that measures human-model alignment in curiosity through linguistic (style), topic preference (content) analysis and grounding insights in social science constructs. Across open- and closed-source models, we find that LLMs flatten cross-cultural diversity, aligning more closely with how curiosity is expressed in Western countries. We then explore fine-tuning strategies to induce curiosity in LLMs, narrowing the human-model alignment gap by up to 50%. Finally, we demonstrate the practical value of curiosity for LLM adaptability across cultures, showing its importance for future NLP research.
Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task performance) through a curiosity coefficient. Yet it has been unclear when this balance yields both coherent learning and efficient decision-making: insufficient curiosity can drive myopic exploitation and prevent uncertainty resolution, while excessive curiosity can induce unnecessary exploration and regret. We establish the first theoretical guarantee for EFE-minimizing agents, showing that a single requirement--sufficient curiosity--simultaneously ensures self-consistent learning (Bayesian posterior consistency) and no-regret optimization (bounded cumulative regret). Our analysis characterizes how this mechanism depends on initial uncertainty, identifiability, and objective alignment, thereby connecting AIF to classical Bayesian experimental design and Bayesian optimization within one theoretical framework. We further translate these theories into practical design guidelines for tuning the epistemic-pragmatic trade-off in hybrid learning-optimization problems, validated through real-world experiments.
This study delves into the mechanisms that spark user curiosity driving active engagement within public Telegram groups. By analyzing approximately 6 million messages from 29,196 users across 409 groups, we identify and quantify the key factors that stimulate users to actively participate (i.e., send messages) in group discussions. These factors include social influence, novelty, complexity, uncertainty, and conflict, all measured through metrics derived from message sequences and user participation over time. After clustering the messages, we apply explainability techniques to assign meaningful labels to the clusters. This approach uncovers macro categories representing distinct curiosity stimulation profiles, each characterized by a unique combination of various stimuli. Social influence from peers and influencers drives engagement for some users, while for others, rare media types or a diverse range of senders and media sparks curiosity. Analyzing patterns, we found that user curiosity stimuli are mostly stable, but, as the time between the initial message increases, curiosity occasionally shifts. A graph-based analysis of influence networks reveals that users motivated by direc
Social media platforms are often criticized for fostering antisocial behavior rather than prosocial behavior. Yet, testing interventions to encourage prosocial dispositions, such as open-mindedness, has been hindered by researchers' limited ability to manipulate platform features and isolate causal effects in commercial environments. We address this challenge through a randomized controlled trial with 2,282 U.S. adults conducted on a new research platform we developed that uses AI bots to replicate live social media dynamics while enabling controlled experimentation. Participants engaged in 15-minute discussions about energy and climate topics, with treatment groups exposed to curiosity priming either through modified on-platform social norms, interface affordances, or both. Results demonstrate that curiosity priming significantly increased question-asking behavior and textual measures of curiosity in user posts, while also reducing toxicity. Although interventions decreased generic engagement behaviors like liking and commenting, they had no significant negative impact on reported app enjoyment or time spent writing posts and replies. Leveraging experimental control over platform
This study examines the impact of an Artificial Intelligence tutor teammate (AI) on student curiosity-driven engagement and learning effectiveness during Interactive Molecular Dynamics (IMD) tasks on the Visual Molecular Dynamics platform. It explores the role of the AI's curiosity-triggering and response behaviors in stimulating and sustaining student curiosity, affecting the frequency and complexity of student-initiated questions. The study further assesses how AI interventions shape student engagement, foster discovery curiosity, and enhance team performance within the IMD learning environment. Using a Wizard-of-Oz paradigm, a human experimenter dynamically adjusts the AI tutor teammate's behavior through a large language model. By employing a mixed-methods exploratory design, a total of 11 high school students participated in four IMD tasks that involved molecular visualization and calculations, which increased in complexity over a 60-minute period. Team performance was evaluated through real-time observation and recordings, whereas team communication was measured by question complexity and AI's curiosity-triggering and response behaviors. Cross Recurrence Quantification Analys
This chapter examines the relationship between curiosity and metacognition as critical drivers of autonomous and self-regulated learning. We synthesize recent research to propose a unified framework integrating behavioral, computational, and psychoeducational dimensions, arguing that curiosity, i.e. the intrinsic drive to acquire new knowledge, relies fundamentally on metacognitive monitoring and control. From an educational perspective, we evaluate interventions designed to enhance curiosity in classroom settings. While promising, our review indicates that these interventions yield mixed results, often proving differentially effective for struggling learners, thereby underscoring the necessity for approaches tailored to individual profiles. Finally, we address the paradigm shift introduced by Generative AI. While Large Language Models (LLMs) offer unprecedented scalability for personalized inquiry, we argue that their default interaction modes pose significant risks to the dynamics of curiosity-driven learning. To mitigate these challenges, we review strategies to transform AI from a potential cognitive shortcut into a powerful partner for sustained epistemic development.
What drives an agent to explore the world while also maintaining control over the environment? From a child at play to scientists in the lab, intelligent agents must balance curiosity (the drive to seek knowledge) with competence (the drive to master and control the environment). Bridging cognitive theories of intrinsic motivation with reinforcement learning, we ask how evolving internal representations mediate the trade-off between curiosity (novelty or information gain) and competence (empowerment). We compare two model-based agents using handcrafted state abstractions (Tabular) or learning an internal world model (Dreamer). The Tabular agent shows curiosity and competence guide exploration in distinct patterns, while prioritizing both improves exploration. The Dreamer agent reveals a two-way interaction between exploration and representation learning, mirroring the developmental co-evolution of curiosity and competence. Our findings formalize adaptive exploration as a balance between pursuing the unknown and the controllable, offering insights for cognitive theories and efficient reinforcement learning.
Food is a key pleasure of traveling, but travelers face a trade-off between exploring curious new local food and choosing comfortable, familiar options. This creates demand for personalized recommendation systems that balance these competing factors. To the best of our knowledge, conventional recommendation methods cannot provide recommendations that offer both curiosity and comfort for food unknown to the user at a travel destination. In this study, we propose new quantitative methods for estimating comfort and curiosity: Kernel Density Scoring (KDS) and Mahalanobis Distance Scoring (MDS). KDS probabilistically estimates food history distribution using kernel density estimation, while MDS uses Mahalanobis distances between foods. These methods score food based on how their representation vectors fit the estimated distributions. We also propose a ranking method measuring the balance between comfort and curiosity based on taste and ingredients. This balance is defined as curiosity (return) gained per unit of comfort (risk) in choosing a food. For evaluation the proposed method, we newly collected a dataset containing user surveys on Japanese food and assessments of foreign food rega
Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions. We introduce Curiosity-Critic, which grounds its intrinsic reward in the improvement of this cumulative objective, and show that it admits a tractable per-step surrogate: the difference between the current prediction error and the asymptotic error baseline of the current state transition. We estimate this error baseline online with a learned critic co-trained alongside the world model; regressing a single scalar, the critic converges well before the world model saturates, redirecting exploration toward learnable transitions without oracle knowledge of the noise floor. The reward is higher for learnable transitions and collapses toward the error baseline for stochastic ones, effectively separating epistemic (reducible) from aleatoric (irreducible) prediction error online. Prior prediction-error curiosity formulations, from Schmidhuber (1991) to learned-feature-space variants, emerge as special cases corresponding to specific approximations of this error baseline. Experiments on a stochastic grid world show th
During virtual navigation, users exhibit varied interaction and navigation behaviors influenced by several factors. Existing theories and models have been developed to explain and predict these diverse patterns. While users often experience uncomfortable sensations, such as cybersickness, during virtual reality (VR) use, they do not always make optimal decisions to mitigate these effects. Although methods like reinforcement learning have been used to model decision-making processes, they typically rely on random selection to simulate actions, failing to capture the complexities of real navigation behavior. In this study, we propose curiosity as a key factor driving irrational decision-making, suggesting that users continuously balance exploration and cybersickness according to the free energy principle during virtual navigation. Our findings show that VR users generally adopt conservative strategies when navigating, with most participants displaying negative curiosity across trials. However, curiosity levels tend to rise when the virtual environment changes, illustrating the dynamic interplay between exploration and discomfort. This study provides a quantitative approach to decodin
Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein's Information Gap Theory, we introduce a framework that models reader curiosity by quantifying semantic information gaps within a text's semantic structure. Our approach leverages BERTopic-inspired topic modeling and persistent homology to analyze the evolving topology (connected components, cycles, voids) of a dynamic semantic network derived from text segments, treating these features as proxies for information gaps. To empirically evaluate this pipeline, we collect reader curiosity ratings from participants (n = 49) as they read S. Collins's ''The Hunger Games'' novel. We then use the topological features from our pipeline as independent variables to predict these ratings, and experimentally show that they significantly improve curiosity prediction compared to a baseline model (73% vs. 30% explained deviance), validating our approach. This pipeline offers a new computational method for analyzing text structure and its relation to reader engagement.
Mathematics is changing. Computers are verifying proofs, checking calculations, and exploring complex structures that would overwhelm human effort. Yet curiosity-driven research is where tomorrow's breakthroughs are quietly prepared. In this invited article for the VSH-AEU Bulletin, these themes are illustrated through anecdotes centered on a mathematical object central to the author's work: the lattice.
One of the bottlenecks in robotic intelligence is the instability of neural network models, which, unlike control models, lack a well-defined convergence domain and stability. This leads to risks when applying intelligence in the physical world. Specifically, imitation policy based on neural network may generate hallucinations, leading to inaccurate behaviors that impact the safety of real-world applications. To address this issue, this paper proposes the Curiosity-Diffuser, aimed at guiding the conditional diffusion model to generate trajectories with lower curiosity, thereby improving the reliability of policy. The core idea is to use a Random Network Distillation (RND) curiosity module to assess whether the model's behavior aligns with the training data, and then minimize curiosity by classifier guidance diffusion to reduce overgeneralization during inference. Additionally, we propose a computationally efficient metric for evaluating the reliability of the policy, measuring the similarity between the generated behaviors and the training dataset, to facilitate research about reliability learning. Finally, simulation verify the effectiveness and applicability of the proposed metho
Curiosity is a vital metacognitive skill in educational contexts, leading to creativity, and a love of learning. And while many school systems increasingly undercut curiosity by teaching to the test, teachers are increasingly interested in how to evoke curiosity in their students to prepare them for a world in which lifelong learning and reskilling will be more and more important. One aspect of curiosity that has received little attention, however, is the role of peers in eliciting curiosity. We present what we believe to be the first theoretical framework that articulates an integrated socio-cognitive account of curiosity that ties observable behaviors in peers to underlying curiosity states. We make a bipartite distinction between individual and interpersonal functions that contribute to curiosity, and multimodal behaviors that fulfill these functions. We validate the proposed framework by leveraging a longitudinal latent variable modeling approach. Findings confirm a positive predictive relationship between the latent variables of individual and interpersonal functions and curiosity, with the interpersonal functions exercising a comparatively stronger influence. Prominent behavi
The sparsity of extrinsic rewards poses a serious challenge for reinforcement learning (RL). Currently, many efforts have been made on curiosity which can provide a representative intrinsic reward for effective exploration. However, the challenge is still far from being solved. In this paper, we present a novel curiosity for RL, named DyMeCu, which stands for Dynamic Memory-based Curiosity. Inspired by human curiosity and information theory, DyMeCu consists of a dynamic memory and dual online learners. The curiosity arouses if memorized information can not deal with the current state, and the information gap between dual learners can be formulated as the intrinsic reward for agents, and then such state information can be consolidated into the dynamic memory. Compared with previous curiosity methods, DyMeCu can better mimic human curiosity with dynamic memory, and the memory module can be dynamically grown based on a bootstrap paradigm with dual learners. On multiple benchmarks including DeepMind Control Suite and Atari Suite, large-scale empirical experiments are conducted and the results demonstrate that DyMeCu outperforms competitive curiosity-based methods with or without extrin
To address the problem of narrow recommendation ranges caused by an emphasis on prediction accuracy, serendipitous recommendations, which consider both usefulness and unexpectedness, have attracted attention. However, realizing serendipitous recommendations is challenging due to the varying proportions of usefulness and unexpectedness preferred by different users, which is influenced by their differing desires for knowledge. In this paper, we propose a method to estimate the proportion of usefulness and unexpectedness that each user desires based on their curiosity, and make recommendations that match this preference. The proposed method estimates a user's curiosity by considering both their long-term and short-term interests. Offline experiments were conducted using the MovieLens-1M dataset to evaluate the effectiveness of the proposed method. The experimental results demonstrate that our method achieves the same level of performance as state-of-the-art method while successfully providing serendipitous recommendations.
The autonomous learning of new goals in robotics remains a complex issue to address. Here, we propose a model where curiosity influence learning flexibility. To do so, this paper proposes to root curiosity and attention together by taking inspiration from the Locus Coeruleus-Norepinephrine system along with various cognitive processes such as cognitive persistence and visual habituation. We apply our approach by experimenting with a simulated robotic arm on a set of objects with varying difficulty. The robot first discovers new goals via bottom-up attention through motor babbling with an inhibition of return mechanism, then engage to the learning of goals due to neural activity arising within the curiosity mechanism. The architecture is modelled with dynamic neural fields and the learning of goals such as pushing the objects in diverse directions is supported by the use of forward and inverse models implemented by multi-layer perceptrons. The adoption of dynamic neural fields to model curiosity, habituation and persistence allows the robot to demonstrate various learning trajectories depending on the object. In addition, the approach exhibits interesting properties regarding the le
Curiosity is one of the main motives in many of the natural creatures with measurable levels of intelligence for exploration and, as a result, more efficient learning. It makes it possible for humans and many animals to explore efficiently by searching for being in states that make them surprised with the goal of learning more about what they do not know. As a result, while being curious, they learn better. In the machine learning literature, curiosity is mostly combined with reinforcement learning-based algorithms as an intrinsic reward. This work proposes an algorithm based on the drive of curiosity for autonomous learning to control by generating proper motor speeds from odometry data. The quadcopter controlled by our proposed algorithm can pass through obstacles while controlling the Yaw direction of the quad-copter toward the desired location. To achieve that, we also propose a new curiosity approach based on prediction error. We ran tests using on-policy, off-policy, on-policy plus curiosity, and the proposed algorithm and visualized the effect of curiosity in evolving exploration patterns. Results show the capability of the proposed algorithm to learn optimal policy and maxi