arXiv subjects

Cleotilde Gonzalez

Publications and source records attributed to Cleotilde Gonzalez.

At least 19 recordsLinked to original sources

arXiv2026

Align AI to Dynamic Human-AI Workflows

Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions. In this paper, we argue for a shift from static and emulative to interactive and complementary alignment, where preferences emerge through interaction and alignment is defined not by satisfying preferences alone. We first formalize this gap by contrasting existing alignment with a trajectory-level view in which human and model behavior co-evolve over time. Because these interaction dynamics have not been adequately captured within existing ML formulations, we ground this perspective in insights from an interdisciplinary workshop. We draw on lessons from social-science accounts of human-human collaboration and then argue that human-AI systems amplify these dynamics, introducing new asymmetries that make reasoning about uncertainty harder and introduce new coordination challenges. Based on these lessons and new challenges, we conclude by outlining a research agenda for developing AI systems that align with humans in interaction, requiring an interdisciplinary synthesis of machine learning and the social and decision sciences.

cs.AI↗

arXiv2026

Computational Modeling of Human Adaptation in Urban Infrastructure Management under Extreme Conditions: A Case Study of Subway Flood Scenarios

Decision-making in urban infrastructure management during extreme events relies heavily on human operators, yet current computational support systems often fail to account for non-monotonic human adaptation and latent psychological biases like overconfidence and defensive overcorrection. This study addresses this gap by integrating Instance-Based Learning Theory (IBLT) into the domain of civil engineering computing. We establish a computational cognitive architecture that simulates operator decision processes through the mathematical mechanisms of memory retrieval and utility blending. This model functions as a computational baseline, representing boundedly rational adaptation driven by experiential priors, thus allowing for the algorithmic isolation of latent psychological biases from the baseline dynamics of memory-based learning. We demonstrated this framework using a human-in-the-loop microworld experiment simulating subway flood-induced track suspensions, where dispatchers must balance passenger safety against service efficiency. Analysis revealed a complex, non-linear human adaptation cycle consisting of four phases: acquisition, overconfidence, overcorrection, and recalibration. Specifically, the computational model exposed a significant divergence during the post-accident "overcorrection" phase: while human operators exhibited immediate, defensive risk overestimation, the model maintained a stable trajectory based on accumulated experience. This strategic divergence confirms that operational instability following failure is often attributable to acute psychological bias overriding stable memory-based adaptation, a pattern theoretically expected to recur across analogous high-stakes environments and validatable through multi-modal behavioral and sensor data from professional operators.

cs.HC↗

arXiv2026

CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation

The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and questions for regarding how humans interact with autonomous agents. Multi-agent experiments, where humans and AI act together, can offer important opportunities to study social decision making, but there is a lack of accessible tooling available to researchers to run such experiments. We introduce two tools designed to reduce these barriers. The first, CoGrid, is a multi-agent grid-based simulation library with dual NumPy and JAX backends. The second, Multi-User Gymnasium (MUG), translates such simulation environments directly into interactive web-based experiments. MUG supports interactions with arbitrary numbers of humans and AI, utilizing either server-authoritative or peer-to-peer networking with rollback netcode to account for latency. Together, these tools can enable researchers to deploy studies of human-AI interaction, facilitating inquiry into core questions of psychology, cognition, and decision making and their relationship to human-AI interaction. Both tools are open source and available to the broader research community. Documentation and source code is available at {cogrid, multi-user-gymnasium}.readthedocs.io. This paper details the functionality of these tools and presents several case studies to illustrate their utility in human-AI multi-agent experimentation.

cs.HC↗

arXiv2026

Dynamic Theory of Mind as a Temporal Memory Problem: Evidence from Large Language Models

Theory of Mind (ToM) is central to social cognition and human-AI interaction, and Large Language Models (LLMs) have been used to help understand and represent ToM. However, most evaluations treat ToM as a static judgment at a single moment, primarily relying on tests of false beliefs. This overlooks a key dynamic dimension of ToM: the ability to represent, update, and retrieve others' beliefs over time. We investigate dynamic ToM as a temporally extended representational memory problem, asking whether LLMs can track belief trajectories across interactions rather than only inferring current beliefs. We introduce DToM-Track, an evaluation framework to investigate temporal belief reasoning in controlled multiturn conversations, testing the recall of beliefs held prior to an update, the inference of current beliefs, and the detection of belief change. Using LLMs as computational probes, we find a consistent asymmetry: models reliably infer an agent's current belief but struggle to maintain and retrieve prior belief states once updates occur. This pattern persists across LLM model families and scales, and is consistent with recency bias and interference effects well documented in cognitive science. These results suggest that tracking belief trajectories over time poses a distinct challenge beyond classical false-belief reasoning. By framing ToM as a problem of temporal representation and retrieval, this work connects ToM to core cognitive mechanisms of memory and interference and exposes the implications for LLM models of social reasoning in extended human-AI interactions.

cs.AI↗

arXiv2025

Exploring the Role of Theory of Mind in Human Decision Making: Cognitive, Spatial, and Emotional Influences in the Adversarial Rock-Paper-Scissors Game

Understanding how humans attribute beliefs, goals, and intentions to others, known as theory of mind (ToM), is critical in the context of human-computer interaction. Despite various metrics used to assess ToM, the interplay between cognitive, spatial, and emotional factors in influencing human decision making during adversarial interactions remains underexplored. This paper investigates these relationships using the Rock-Paper-Scissors (RPS) game as a testbed. Through established ToM tests, we analyze how cognitive reasoning, spatial awareness, and emotional perceptiveness affect human performance when interacting with bots and human opponents in repeated RPS settings. Our findings reveal significant correlations among certain ToM metrics and highlight humans' ability to detect patterns in opponents' actions. However, most individual ToM metrics proved insufficient for predicting performance variations, with recursive thinking being the only metric moderately associated with decision effectiveness. Through exploratory factor analysis (EFA) and structural equation modeling (SEM), we identified two latent factors influencing decision effectiveness: Factor 1, characterized by recursive thinking, emotional perceptiveness, and spatial reasoning, positively affects decision-making against dynamic bots and human players, while Factor 2, linked to interpersonal skills and rational ability, has a negative impact. These insights lay the groundwork for further research on ToM metrics and for designing more intuitive, adaptive systems that better anticipate and adapt to human behavior, ultimately enhancing human-machine collaboration.

cs.HC↗

arXiv2025

Evidence of Cognitive Biases in Capture-the-Flag Cybersecurity Competitions

Understanding how cognitive biases influence adversarial decision-making is essential for developing effective cyber defenses. Capture-the-Flag (CTF) competitions provide an ecologically valid testbed to study attacker behavior at scale, simulating real-world intrusion scenarios under pressure. We analyze over 500,000 submission logs from picoCTF, a large educational CTF platform, to identify behavioral signatures of cognitive biases with defensive implications. Focusing on availability bias and the sunk cost fallacy, we employ a mixed-methods approach combining qualitative coding, descriptive statistics, and generalized linear modeling. Our findings show that participants often submitted flags with correct content but incorrect formatting (availability bias), and persisted in attempting challenges despite repeated failures and declining success probabilities (sunk cost fallacy). These patterns reveal that biases naturally shape attacker behavior in adversarial contexts. Building on these insights, we outline a framework for bias-informed adaptive defenses that anticipate, rather than simply react to, adversarial actions.

cs.CR↗

arXiv2025

Measuring Implicit Spatial Coordination in Teams: Effects on Collective Intelligence and Performance

Coordinated teamwork is essential in fast-paced decision-making environments that require dynamic adaptation, often without an opportunity for explicit communication. Although implicit coordination has been extensively considered in the existing literature, the majority of work has focused on co-located, synchronous teamwork (such as sports teams) or, in distributed teams, primarily on coordination of knowledge work. However, many teams (firefighters, military, law enforcement, emergency response) must coordinate their movements in physical space without the benefit of visual cues or extensive explicit communication. This paper investigates how three dimensions of spatial coordination, namely exploration diversity, movement specialization, and adaptive spatial proximity, influence team performance in a collaborative online search and rescue task where explicit communication is restricted and team members rely on movement patterns to infer others' intentions and coordinate actions. Our metrics capture the relational aspects of teamwork by measuring spatial proximity, distribution patterns, and alignment of movements within shared environments. We analyze data from 34 four-person teams (136 participants) assigned to specialized roles in a search and rescue task. Results show that spatial specialization positively predicts performance, while adaptive spatial proximity exhibits a marginal inverted U-shaped relationship, suggesting moderate levels of adaptation are optimal. Furthermore, the temporal dynamics of these metrics differentiate high- from low-performing teams over time. These findings provide insights into implicit spatial coordination in role-based teamwork and highlight the importance of balanced adaptive strategies, with implications for training and AI-assisted team support systems.

cs.AI↗

arXiv2025

Controllable Complementarity: Subjective Preferences in Human-AI Collaboration

Research on human-AI collaboration often prioritizes objective performance. However, understanding human subjective preferences is essential to improving human-AI complementarity and human experiences. We investigate human preferences for controllability in a shared workspace task with AI partners using Behavior Shaping (BS), a reinforcement learning algorithm that allows humans explicit control over AI behavior. In one experiment, we validate the robustness of BS in producing effective AI policies relative to self-play policies, when controls are hidden. In another experiment, we enable human control, showing that participants perceive AI partners as more effective and enjoyable when they can directly dictate AI behavior. Our findings highlight the need to design AI that prioritizes both task performance and subjective human preferences. By aligning AI behavior with human preferences, we demonstrate how human-AI complementarity can extend beyond objective outcomes to include subjective preferences.

cs.HC↗

arXiv2025

Training Users Against Human and GPT-4 Generated Social Engineering Attacks

In real-world decision making, outcomes are often delayed, meaning individuals must make multiple decisions before receiving any feedback. Moreover, feedback can be presented in different ways: it may summarize the overall results of multiple decisions (aggregated feedback) or report the outcome of individual decisions after some delay (clustered feedback). Despite its importance, the timing and presentation of delayed feedback has received little attention in cognitive modeling of decision-making, which typically focuses on immediate feedback. To address this, we conducted an experiment to compare the effect of delayed vs. immediate feedback and aggregated vs. clustered feedback. We also propose a Hierarchical Instance-Based Learning (HIBL) model that captures how people make decisions in delayed feedback settings. HIBL uses a super-model that chooses between sub-models to perform the decision-making task until an outcome is observed. Simulations show that HIBL best predicts human behavior and specific patterns, demonstrating the flexibility of IBL models.

cs.HC↗

arXiv2025

Modeling Attention during Dimensional Shifts with Counterfactual and Delayed Feedback

Attention can be used to inform choice selection in contextual bandit tasks even when context features have not been previously experienced. One example of this is in dimensional shifts, where additional feature values are introduced and the relationship between features and outcomes can either be static or variable. Attentional mechanisms have been extensively studied in contextual bandit tasks where the feedback of choices is provided immediately, but less research has been done on tasks where feedback is delayed or in counterfactual feedback cases. Some methods have successfully modeled human attention with immediate feedback based on reward prediction errors (RPEs), though recent research raises questions of the applicability of RPEs onto more general attentional mechanisms. Alternative models suggest that information theoretic metrics can be used to model human attention, with broader applications to novel stimuli. In this paper, we compare two different methods for modeling how humans attend to specific features of decision making tasks, one that is based on calculating an information theoretic metric using a memory of past experiences, and another that is based on iteratively updating attention from reward prediction errors. We compare these models using simulations in a contextual bandit task with both intradimensional and extradimensional domain shifts, as well as immediate, delayed, and counterfactual feedback. We find that calculating an information theoretic metric over a history of experiences is best able to account for human-like behavior in tasks that shift dimensions and alter feedback presentation. These results indicate that information theoretic metrics of attentional mechanisms may be better suited than RPEs to predict human attention in decision making, though further studies of human behavior are necessary to support these results.

cs.LG↗

arXiv2024

Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content

Cosine similarity between two documents can be computed using token embeddings formed by Large Language Models (LLMs) such as GPT-4, and used to categorize those documents across a range of uses. However, these similarities are ultimately dependent on the corpora used to train these LLMs, and may not reflect subjective similarity of individuals or how their biases and constraints impact similarity metrics. This lack of cognitively-aware personalization of similarity metrics can be particularly problematic in educational and recommendation settings where there is a limited number of individual judgements of category or preference, and biases can be particularly relevant. To address this, we rely on an integration of an Instance-Based Learning (IBL) cognitive model with LLM embeddings to develop the Instance-Based Individualized Similarity (IBIS) metric. This similarity metric is beneficial in that it takes into account individual biases and constraints in a manner that is grounded in the cognitive mechanisms of decision making. To evaluate the IBIS metric, we also introduce a dataset of human categorizations of emails as being either dangerous (phishing) or safe (ham). This dataset is used to demonstrate the benefits of leveraging a cognitive model to measure the subjective similarity of human participants in an educational setting.

cs.CL↗

arXiv2024

Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models

For public health programs with limited resources, the ability to predict how behaviors change over time and in response to interventions is crucial for deciding when and to whom interventions should be allocated. Using data from a real-world maternal health program, we demonstrate how a cognitive model based on Instance-Based Learning (IBL) Theory can augment existing purely computational approaches. Our findings show that, compared to general time-series forecasters (e.g., LSTMs), IBL models, which reflect human decision-making processes, better predict the dynamics of individuals' states. Additionally, IBL provides estimates of the volatility in individuals' states and their sensitivity to interventions, which can improve the efficiency of training of other time series models.

cs.LG↗

arXiv2024

Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans

Modeling human cognitive processes in dynamic decision-making tasks has been an endeavor in AI for a long time because such models can help make AI systems more intuitive, personalized, mitigate any human biases, and enhance training in simulation. Some initial work has attempted to utilize neural networks (and large language models) but often assumes one common model for all humans and aims to emulate human behavior in aggregate. However, the behavior of each human is distinct, heterogeneous, and relies on specific past experiences in certain tasks. For instance, consider two individuals responding to a phishing email: one who has previously encountered and identified similar threats may recognize it quickly, while another without such experience might fall for the scam. In this work, we build on Instance Based Learning (IBL) that posits that human decisions are based on similar situations encountered in the past. However, IBL relies on simple fixed form functions to capture the mapping from past situations to current decisions. To that end, we propose two new attention-based neural network models to have open form non-linear functions to model distinct and heterogeneous human decision-making in dynamic settings. We experiment with two distinct datasets gathered from human subject experiment data, one focusing on detection of phishing email by humans and another where humans act as attackers in a cybersecurity setting and decide on an attack option. We conducted extensive experiments with our two neural network models, IBL, and GPT3.5, and demonstrate that the neural network models outperform IBL significantly in representing human decision-making, while providing similar interpretability of human decisions as IBL. Overall, our work yields promising results for further use of neural networks in cognitive modeling of human decision making.

cs.LG↗

arXiv2024

Predicting and Understanding Human Action Decisions: Insights from Large Language Models and Cognitive Instance-Based Learning

Large Language Models (LLMs) have demonstrated their capabilities across various tasks, from language translation to complex reasoning. Understanding and predicting human behavior and biases are crucial for artificial intelligence (AI) assisted systems to provide useful assistance, yet it remains an open question whether these models can achieve this. This paper addresses this gap by leveraging the reasoning and generative capabilities of the LLMs to predict human behavior in two sequential decision-making tasks. These tasks involve balancing between exploitative and exploratory actions and handling delayed feedback, both essential for simulating real-life decision processes. We compare the performance of LLMs with a cognitive instance-based learning (IBL) model, which imitates human experiential decision-making. Our findings indicate that LLMs excel at rapidly incorporating feedback to enhance prediction accuracy. In contrast, the cognitive IBL model better accounts for human exploratory behaviors and effectively captures loss aversion bias, i.e., the tendency to choose a sub-optimal goal with fewer step-cost penalties rather than exploring to find the optimal choice, even with limited experience. The results highlight the benefits of integrating LLMs with cognitive architectures, suggesting that this synergy could enhance the modeling and understanding of complex human decision-making patterns.

cs.AI↗

arXiv2023

Learning in Cooperative Multiagent Systems Using Cognitive and Machine Models

Developing effective Multi-Agent Systems (MAS) is critical for many applications requiring collaboration and coordination with humans. Despite the rapid advance of Multi-Agent Deep Reinforcement Learning (MADRL) in cooperative MAS, one major challenge is the simultaneous learning and interaction of independent agents in dynamic environments in the presence of stochastic rewards. State-of-the-art MADRL models struggle to perform well in Coordinated Multi-agent Object Transportation Problems (CMOTPs), wherein agents must coordinate with each other and learn from stochastic rewards. In contrast, humans often learn rapidly to adapt to nonstationary environments that require coordination among people. In this paper, motivated by the demonstrated ability of cognitive models based on Instance-Based Learning Theory (IBLT) to capture human decisions in many dynamic decision making tasks, we propose three variants of Multi-Agent IBL models (MAIBL). The idea of these MAIBL algorithms is to combine the cognitive mechanisms of IBLT and the techniques of MADRL models to deal with coordination MAS in stochastic environments from the perspective of independent learners. We demonstrate that the MAIBL models exhibit faster learning and achieve better coordination in a dynamic CMOTP task with various settings of stochastic rewards compared to current MADRL models. We discuss the benefits of integrating cognitive insights into MADRL models.

cs.AI↗

arXiv2023

Credit Assignment: Challenges and Opportunities in Developing Human-like AI Agents

Temporal credit assignment is crucial for learning and skill development in natural and artificial intelligence. While computational methods like the TD approach in reinforcement learning have been proposed, it's unclear if they accurately represent how humans handle feedback delays. Cognitive models intend to represent the mental steps by which humans solve problems and perform a number of tasks, but limited research in cognitive science has addressed the credit assignment problem in humans and cognitive models. Our research uses a cognitive model based on a theory of decisions from experience, Instance-Based Learning Theory (IBLT), to test different credit assignment mechanisms in a goal-seeking navigation task with varying levels of decision complexity. Instance-Based Learning (IBL) models simulate the process of making sequential choices with different credit assignment mechanisms, including a new IBL-TD model that combines the IBL decision mechanism with the TD approach. We found that (1) An IBL model that gives equal credit assignment to all decisions is able to match human performance better than other models, including IBL-TD and Q-learning; (2) IBL-TD and Q-learning models underperform compared to humans initially, but eventually, they outperform humans; (3) humans are influenced by decision complexity, while models are not. Our study provides insights into the challenges of capturing human behavior and the potential opportunities to use these models in future AI systems to support human activities.

cs.AI↗

arXiv2023

Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games

Designing cyber defense systems to account for cognitive biases in human decision making has demonstrated significant success in improving performance against human attackers. However, much of the attention in this area has focused on relatively simple accounts of biases in human attackers, and little is known about adversarial behavior or how defenses could be improved by disrupting attacker's behavior. In this work, we present a novel model of human decision-making inspired by the cognitive faculties of Instance-Based Learning Theory, Theory of Mind, and Transfer of Learning. This model functions by learning from both roles in a security scenario: defender and attacker, and by making predictions of the opponent's beliefs, intentions, and actions. The proposed model can better defend against attacks from a wide range of opponents compared to alternatives that attempt to perform optimally without accounting for human biases. Additionally, the proposed model performs better against a range of human-like behavior by explicitly modeling human transfer of learning, which has not yet been applied to cyber defense scenarios. Results from simulation experiments demonstrate the potential usefulness of cognitively inspired models of agents trained in attack and defense roles and how these insights could potentially be used in real-world cybersecurity.

cs.AI↗

arXiv2023

Learning About Simulated Adversaries from Human Defenders using Interactive Cyber-Defense Games

Given the increase in cybercrime, cybersecurity analysts (i.e. Defenders) are in high demand. Defenders must monitor an organization's network to evaluate threats and potential breaches into the network. Adversary simulation is commonly used to test defenders' performance against known threats to organizations. However, it is unclear how effective this training process is in preparing defenders for this highly demanding job. In this paper, we demonstrate how to use adversarial algorithms to investigate defenders' learning of defense strategies, using interactive cyber defense games. Our Interactive Defense Game (IDG) represents a cyber defense scenario that requires constant monitoring of incoming network alerts and allows a defender to analyze, remove, and restore services based on the events observed in a network. The participants in our study faced one of two types of simulated adversaries. A Beeline adversary is a fast, targeted, and informed attacker; and a Meander adversary is a slow attacker that wanders the network until it finds the right target to exploit. Our results suggest that although human defenders have more difficulty to stop the Beeline adversary initially, they were able to learn to stop this adversary by taking advantage of their attack strategy. Participants who played against the Beeline adversary learned to anticipate the adversary and take more proactive actions, while decreasing their reactive actions. These findings have implications for understanding how to help cybersecurity analysts speed up their training.

cs.CR↗