arXiv subjects

Kent Larson

Publications and source records attributed to Kent Larson.

At least 19 recordsLinked to original sources

arXiv2026

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

Majority voting is the default unsupervised aggregator for multi-sample LLM inference, but it discards two signals: within-group answer entropy and between-group reasoning geometry. We aggregate by delegation instead (Propagational Proxy Voting, PPV): each group of samples keeps weight on its own answer in proportion to its entropy-based confidence (When) and routes the rest to peers by reasoning-embedding similarity (Whom); the stationary distribution of the resulting delegation matrix picks the consensus answer. This requires neither gold labels nor training. On MMLU-Pro with 128 samples per question, delegation beats majority by +1.5 pp overall and +2.24 pp on non-trivial questions (McNemar p ~ 1.0e-14, n = 8,099), overturning wrong majorities whose answer cluster is geometrically incoherent while the correct minority is tight. We then characterize exactly when delegation overturns majority: a two-option model gives a closed-form flip condition on each option's confidence and the weight it routes to the other, with a do-no-harm corollary for near-unanimous questions. The condition calls the realized winner on 96.5% of non-trivial questions, and its predicted mass gap tracks the realized gap at r = 0.97. We did not find any other unsupervised ensemble methods that close the oracle gap.

cs.AI↗

arXiv2026

Do Robots Need Body Language? Comparing Communication Modalities for Legible Motion Intent in Human-Shared Spaces

Robots in shared spaces often move in ways that are difficult for people to interpret, placing the burden on humans to adapt. High-DoF robots exhibit motion that people read as expressive, intentionally or not, making it important to understand how such cues are perceived. We present an online video study evaluating how different signaling modalities, expressive motion, lights, text, and audio, shape people's ability to understand a quadruped robot's upcoming navigation actions (Boston Dynamics Spot). Across four common scenarios, we measure how each modality influences humans' (1) accuracy in predicting the robot's next navigation action, (2) confidence in that prediction, and (3) trust in the robot to act safely. The study tests how expressive motions compare to explicit channels, whether aligned multimodal cues enhance interpretability, and how conflicting cues affect user confidence and trust. We contribute initial evidence on the relative effectiveness of implicit versus explicit signaling strategies.

cs.RO↗

arXiv2025

HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning

Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now approximate human responses at scale, they remain tuned to population-level consensus, often erasing the individuality of reasoning styles and belief trajectories. To advance the vision of more human-like reasoning in machines, we introduce HugAgent (HUman-Grounded AGENT Benchmark), which rethinks human reasoning simulation along three dimensions: (i) from averaged to individualized reasoning, (ii) from behavioral mimicry to cognitive alignment, and (iii) from vignette-based to open-ended data. The benchmark evaluates whether a model can predict a specific person's behavioral responses and the underlying reasoning dynamics in out-of-distribution scenarios, given partial evidence of their prior views. HugAgent combines structured questionnaires with semi-structured think-aloud interviews to collect ecologically valid belief states, belief updates, and reasoning traces from human participants. Our experiments reveal a clear asymmetry: models recover a person's belief state from their own context reasonably well, but struggle to predict belief updates under intervention. Cross-person and cross-domain controls trace this gap to associative matching within a topic rather than identity-consistent reasoning, suggesting that progress requires better-calibrated change detection, not simply more context. We scope the benchmark to self-reported belief reasoning in three policy domains: healthcare, surveillance, and zoning. The benchmark, along with its complete data collection pipeline and companion chatbot, is open-sourced as HugAgent (https://github.com/jajamoa/HugAgent) and TraceYourThinking (https://github.com/jajamoa/trace-your-thinking).

cs.AI↗

arXiv2025

Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain

Understanding human behavior in urban environments is a crucial field within city sciences. However, collecting accurate behavioral data, particularly in newly developed areas, poses significant challenges. Recent advances in generative agents, powered by Large Language Models (LLMs), have shown promise in simulating human behaviors without relying on extensive datasets. Nevertheless, these methods often struggle with generating consistent, context-sensitive, and realistic behavioral outputs. To address these limitations, this paper introduces the Preference Chain, a novel method that integrates Graph Retrieval-Augmented Generation (RAG) with LLMs to enhance context-aware simulation of human behavior in transportation systems. Experiments conducted on the Replica dataset demonstrate that the Preference Chain outperforms standard LLM in aligning with real-world transportation mode choices. The development of the Mobility Agent highlights potential applications of proposed method in urban mobility modeling for emerging cities, personalized travel behavior analysis, and dynamic traffic forecasting. Despite limitations such as slow inference and the risk of hallucination, the method offers a promising framework for simulating complex human behavior in data-scarce environments, where traditional data-driven models struggle due to limited data availability.

cs.AI↗

arXiv2025

Understanding Demand for Shared Autonomous Micro-Mobility

This study examines the behavioral and environmental implications of shared autonomous micro-mobility systems, focusing on autonomous bicycles and their integration with transit in the U.S. While prior research has addressed operational and lifecycle aspects, a critical gap remains in understanding which modes these services are likely to substitute, who is most inclined to adopt them, and how service attributes influence user decisions. We design a context-aware stated preference survey grounded in real-world trips and estimate discrete choice models, including a hybrid model incorporating latent attitudes. Findings indicate that adoption, mode shift, and environmental impacts are highly sensitive to service design. Scenarios with minimal wait and cost yield high adoption but increase emissions, while moderate waits are more likely to reduce impacts. Adoption likelihood varies with demographic characteristics, and outcomes depend on city type, context, and infrastructure assumptions. These insights can inform the development of more sustainable and equitable mobility systems.

cs.ET↗

arXiv2025

Simulating Society Requires Simulating Thought

Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior; it demands cognitively grounded reasoning that is structured, revisable, and traceable. LLM-based agents are increasingly used to emulate individual and group behavior, primarily through prompting and supervised fine-tuning. Yet current simulations remain grounded in a behaviorist "demographics in, behavior out" paradigm, focusing on surface-level plausibility. As a result, they often lack internal coherence, causal reasoning, and belief traceability, making them unreliable for modeling how people reason, deliberate, and respond to interventions. To address this, we present a conceptual modeling paradigm, Generative Minds (GenMinds), which draws from cognitive science to support structured belief representations in generative agents. To evaluate such agents, we introduce the RECAP (REconstructing CAusal Paths) framework, a benchmark designed to assess reasoning fidelity via causal traceability, demographic grounding, and intervention consistency. These contributions advance a broader shift: from surface-level mimicry to generative agents that simulate thought, not just language, for social simulations.

cs.CY↗

arXiv2025

Perspective-Aware AI in Extended Reality

AI-enhanced Extended Reality (XR) aims to deliver adaptive, immersive experiences-yet current systems fall short due to shallow user modeling and limited cognitive context. We introduce Perspective-Aware AI in Extended Reality (PAiR), a foundational framework for integrating Perspective-Aware AI (PAi) with XR to enable interpretable, context-aware experiences grounded in user identity. PAi is built on Chronicles: reasoning-ready identity models learned from multimodal digital footprints that capture users' cognitive and experiential evolution. PAiR employs these models in a closed-loop system linking dynamic user states with immersive environments. We present PAiR's architecture, detailing its modules and system flow, and demonstrate its utility through two proof-of-concept scenarios implemented in the Unity-based OpenDome engine. PAiR opens a new direction for human-AI interaction by embedding perspective-based identity models into immersive systems.

cs.AI↗

arXiv2025

Propagational Proxy Voting

This paper proposes a voting process in which voters allocate fractional votes to their expected utility in different domains: over proposals, other participants, and sets containing proposals and participants. This approach allows for a more nuanced expression of preferences by calculating the result and relevance within each node. We modeled this by creating a voting matrix that reflects their preference. We use absorbing Markov chains to gain the consensus, and also calculate the influence within the participating nodes. We illustrate this method in action through an experiment with 69 students using a budget allocation topic.

cs.SI↗

arXiv2025

Measuring risks inherent to our digital economies using Amazon purchase histories from US consumers

What do pickles and trampolines have in common? In this paper we show that while purchases for these products may seem innocuous, they risk revealing clues about customers' personal attributes - in this case, their race. As online retail and digital purchases become increasingly common, consumer data has become increasingly valuable, raising the risks of privacy violations and online discrimination. This work provides the first open analysis measuring these risks, using purchase histories crowdsourced from (N=4248) US Amazon.com customers and survey data on their personal attributes. With this limited sample and simple models, we demonstrate how easily consumers' personal attributes, such as health and lifestyle information, gender, age, and race, can be inferred from purchases. For example, our models achieve AUC values over 0.9 for predicting gender and over 0.8 for predicting diabetes status. To better understand the risks that highly resourced firms like Amazon, data brokers, and advertisers present to consumers, we measure how our models' predictive power scales with more data. Finally, we measure and highlight how different product categories contribute to inference risk in order to make our findings more interpretable and actionable for future researchers and privacy advocates.

cs.CY↗

arXiv2025

Evaluating Amazon Effects and the Limited Impact of COVID-19 With Purchases Crowdsourced from US Consumers

We leverage a recently published dataset of Amazon purchase histories, crowdsourced from thousands of US consumers, to study how online purchasing behaviors have changed over time, how changes vary across demographic groups, the impact of the COVID-19 pandemic, and relationships between online and offline retail. This work provides a case study in how consumer-level purchases data can reveal purchasing behaviors and trends beyond those available from aggregate metrics. For example, in addition to analyzing spending behavior, we develop new metrics to quantify changes in consumers' online purchase frequency and the diversity of products purchased, to better reflect the growing ubiquity and dominance of online retail. Between 2018 and 2022 these consumer-level metrics grew on average by more than 85%, peaking in 2021. We find a steady upward trend in individuals' online purchasing prior to COVID-19, with a significant increase in the first year of COVID, but without a lasting effect. Purchasing behaviors in 2022 were no greater than the result of the pre-pandemic trend. We also find changes in purchasing significantly differ by demographics, with different responses to the pandemic. We further use the consumer-level data to show substitution effects between online and offline retail in sectors where Amazon heavily invested: books, shoes, and grocery. Prior to COVID we find year-to-year changes in the number of consumers making online purchases for books and shoes negatively correlated with changes in employment at local bookstores and shoe stores. During COVID we find online grocery purchasing negatively correlated with in-store grocery visits. This work demonstrates how crowdsourced, open purchases data can enable economic insights that may otherwise only be available to private firms.

cs.CY↗

arXiv2024

TravelAgent: Generative Agents in the Built Environment

Understanding human behavior in built environments is critical for designing functional, user centered urban spaces. Traditional approaches, such as manual observations, surveys, and simplified simulations, often fail to capture the complexity and dynamics of real world behavior. To address these limitations, we introduce TravelAgent, a novel simulation platform that models pedestrian navigation and activity patterns across diverse indoor and outdoor environments under varying contextual and environmental conditions. TravelAgent leverages generative agents integrated into 3D virtual environments, enabling agents to process multimodal sensory inputs and exhibit human-like decision-making, behavior, and adaptation. Through experiments, including navigation, wayfinding, and free exploration, we analyze data from 100 simulations comprising 1898 agent steps across diverse spatial layouts and agent archetypes, achieving an overall task completion rate of 76%. Using spatial, linguistic, and sentiment analyses, we show how agents perceive, adapt to, or struggle with their surroundings and assigned tasks. Our findings highlight the potential of TravelAgent as a tool for urban design, spatial cognition research, and agent-based modeling. We discuss key challenges and opportunities in deploying generative agents for the evaluation and refinement of spatial designs, proposing TravelAgent as a new paradigm for simulating and understanding human experiences in built environments.

cs.AI↗

arXiv2024

Insights from an experiment crowdsourcing data from thousands of US Amazon users: The importance of transparency, money, and data use

Data generated by users on digital platforms are a crucial resource for advocates and researchers interested in uncovering digital inequities, auditing algorithms, and understanding human behavior. Yet data access is often restricted. How can researchers both effectively and ethically collect user data? This paper shares an innovative approach to crowdsourcing user data to collect otherwise inaccessible Amazon purchase histories, spanning 5 years, from more than 5000 US users. We developed a data collection tool that prioritizes participant consent and includes an experimental study design. The design allows us to study multiple aspects of privacy perception and data sharing behavior. Experiment results (N=6325) reveal both monetary incentives and transparency can significantly increase data sharing. Age, race, education, and gender also played a role, where female and less-educated participants were more likely to share. Our study design enables a unique empirical evaluation of the "privacy paradox", where users claim to value their privacy more than they do in practice. We set up both real and hypothetical data sharing scenarios and find measurable similarities and differences in share rates across these contexts. For example, increasing monetary incentives had a 6 times higher impact on share rates in real scenarios. In addition, we study participants' opinions on how data should be used by various third parties, again finding demographics have a significant impact. Notably, the majority of participants disapproved of government agencies using purchase data yet the majority approved of use by researchers. Overall, our findings highlight the critical role that transparency, incentive design, and user demographics play in ethical data collection practices, and provide guidance for future researchers seeking to crowdsource user generated data.

cs.CY↗

arXiv2024

Shared lightweight autonomous vehicles for urban food deliveries: A simulation study

In recent years, the rapid growth of on-demand deliveries, especially in food deliveries, has spurred the exploration of innovative mobility solutions. In this context, lightweight autonomous vehicles have emerged as a potential alternative. However, their fleet-level behavior remains largely unexplored. To address this gap, we have developed an agent-based model and an environmental impact study assessing the fleet performance of lightweight autonomous food delivery vehicles. This model explores critical factors such as fleet sizing, service level, operational strategies, and environmental impacts. We have applied this model to a case study in Cambridge, MA, USA, where results indicate that there could be environmental benefits in replacing traditional car-based deliveries with shared lightweight autonomous vehicle fleets. Lastly, we introduce an interactive platform that offers a user-friendly means of comprehending the model's performance and potential trade-offs, which can help inform decision-makers in the evolving landscape of food delivery innovation.

cs.CY↗

arXiv2024

TransFlower: An Explainable Transformer-Based Model with Flow-to-Flow Attention for Commuting Flow Prediction

Understanding the link between urban planning and commuting flows is crucial for guiding urban development and policymaking. This research, bridging computer science and urban studies, addresses the challenge of integrating these fields with their distinct focuses. Traditional urban studies methods, like the gravity and radiation models, often underperform in complex scenarios due to their limited handling of multiple variables and reliance on overly simplistic and unrealistic assumptions, such as spatial isotropy. While deep learning models offer improved accuracy, their black-box nature poses a trade-off between performance and explainability -- both vital for analyzing complex societal phenomena like commuting flows. To address this, we introduce TransFlower, an explainable, transformer-based model employing flow-to-flow attention to predict urban commuting patterns. It features a geospatial encoder with an anisotropy-aware relative location encoder for nuanced flow representation. Following this, the transformer-based flow predictor enhances this by leveraging attention mechanisms to efficiently capture flow interactions. Our model outperforms existing methods by up to 30.8% Common Part of Commuters, offering insights into mobility dynamics crucial for urban planning and policy decisions.

cs.LG↗

arXiv2023

zkTax: A pragmatic way to support zero-knowledge tax disclosures

Tax returns contain key financial information of interest to third parties: public officials are asked to share financial data for transparency, companies seek to assess the financial status of business partners, and individuals need to prove their income to landlords or to receive benefits. Tax returns also contain sensitive data such that sharing them in their entirety undermines privacy. We introduce a zero-knowledge tax disclosure system (zkTax) that allows individuals and organizations to make provable claims about select information in their tax returns without revealing additional information, which can be independently verified by third parties. The system consists of three distinct services that can be distributed: a tax authority provides tax documents signed with a public key; a Redact & Prove Service enables users to produce a redacted version of the tax documents with a zero-knowledge proof attesting the provenance of the redacted data; a Verify Service enables anyone to verify the proof. We implement a prototype with a user interface, compatible with U.S. tax forms, and demonstrate how this design could be implemented with minimal changes to existing tax infrastructure. Our system is designed to be extensible to other contexts and jurisdictions. This work provides a practical example of how distributed tools leveraging cryptography can enhance existing government or financial infrastructures, providing immediate transparency alongside privacy without system overhauls.

cs.CR↗

arXiv2023

Fourier series weight in quantum machine learning

In this work, we aim to confirm the impact of the Fourier series on the quantum machine learning model. We will propose models, tests, and demonstrations to achieve this objective. We designed a quantum machine learning leveraged on the Hamiltonian encoding. With a subtle change, we performed the trigonometric interpolation, binary and multiclass classifier, and a quantum signal processing application. We also proposed a block diagram of determining approximately the Fourier coefficient based on quantum machine learning. We performed and tested all the proposed models using the Pennylane framework.

quant-ph↗

arXiv2022

Can autonomy make bicycle-sharing systems more sustainable? Environmental impact analysis of an emerging mobility technology

Autonomous bicycles have recently been proposed as a new and more efficient approach to bicycle-sharing systems (BSS), but the corresponding environmental implications remain unresearched. Conducting environmental impact assessments at an early technological stage is critical to influencing the design and, ultimately, environmental impacts of a system. Consequently, this paper aims to assess the environmental impact of autonomous shared bikes compared with current station-based and dockless systems under different sets of modeling hypotheses and mode-shift scenarios. The results indicate that autonomy could reduce the environmental impact per passenger kilometer traveled of current station-based and dockless BSS by 33.1 % and 58.0 %. The sensitivity analysis shows that the environmental impact of autonomous shared bicycles will mainly depend on vehicle usage rates and the need for infrastructure. Finally, this study highlights the importance of targeting the mode replacement from more polluting modes, especially as traditional mobility modes decarbonize and become more efficient.

econ.GN↗

arXiv2022

Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy

Location data collected from mobile devices represent mobility behaviors at individual and societal levels. These data have important applications ranging from transportation planning to epidemic modeling. However, issues must be overcome to best serve these use cases: The data often represent a limited sample of the population and use of the data jeopardizes privacy. To address these issues, we present and evaluate a system for generating synthetic mobility data using a deep recurrent neural network (RNN) which is trained on real location data. The system takes a population distribution as input and generates mobility traces for a corresponding synthetic population. Related generative approaches have not solved the challenges of capturing both the patterns and variability in individuals' mobility behaviors over longer time periods, while also balancing the generation of realistic data with privacy. Our system leverages RNNs' ability to generate complex and novel sequences while retaining patterns from training data. Also, the model introduces randomness used to calibrate the variation between the synthetic and real data at the individual level. This is to both capture variability in human mobility, and protect user privacy. Location based services (LBS) data from more than 22,700 mobile devices were used in an experimental evaluation across utility and privacy metrics. We show the generated mobility data retain the characteristics of the real data, while varying from the real data at the individual level, and where this amount of variation matches the variation within the real data.

cs.LG↗