Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2607.03621v1 Announce Type: cross Abstract: This paper presents the development and evaluation of a collaborative system for real-time reconstruction of fragmented paper documents in the context of cultural heritage preservation. The developed system includes a collaborative robot, or cobot, that can fully manage the positioning of paper fragments using a specially designed vacuum-based suction attachment. This attachment enables gentle and precise positioning, ensuring the preservation of fragile materials. With this device, we are able to achieve a positioning repeatability of 0.57mm for fragments of 8cm^2. The system offers users the flexibility to choose between manual positioning, with visual guidance, or fully automated positioning performed by the cobot. To further improve the reconstruction process, AI methods for image interpretation, specifically for segmentation and positioning tasks, were applied and evaluated for their applicability to template-based reconstruction o
arXiv:2607.03425v1 Announce Type: cross Abstract: Algorithmic recourse addresses the challenge of providing tailored recommendations to users affected by unfavorable machine learning decisions, in potentially high-stakes scenarios. Traditional approaches to recourse often rely on the closest counterfactual explanations or assume a priori knowledge of a user's causal structure, resulting in interventions that overlook individual contexts and specific feature interactions. To overcome these limitations, we study a human-in-the-loop framework that iteratively approximates the user's structural causal model through interactive queries via Bayesian inference before producing recourse recommendations. This framework exploits humans' feedback to improve the identification of causal effects, allowing personalized recourse that is plausible, cost-effective, and aligned with the actual causal dependencies of each user. As a proof of concept, we evaluate this framework through simulated human res
arXiv:2607.03421v1 Announce Type: cross Abstract: Evaluating search engine results pages (SERPs) to assess result relevance is a demanding step in academic search. In a formative mixed-methods design study, we examine AI-generated SERP-level summaries as a support feature in an academic search engine for social science information. First, we manually evaluated summaries of the top five results for 10 queries using two general-purpose models, one commercial and one open, deriving an exploratory six-category error taxonomy and five safeguards for scholarly deployment. We then conducted a within-subjects user study (n = 30) comparing interfaces with and without AI summaries. Confirmatory analyses showed consistent but non-significant trends favoring AI summaries for subjective workload, perceived usefulness, satisfaction, and decision-making confidence. Exploratory analyses suggested lower mental demand, with frustration also tending to be lower. Behaviorally, participants rarely expanded
arXiv:2607.03289v1 Announce Type: cross Abstract: When designing robots' nonverbal behaviors, many researchers have turned to arts-based insights, such as Disney's Animation Principles. Yet, while these principles bear key insights into the design of like-life characters, their application to robot design is inherently limited, in part because animation is not constrained by real-world physics, and in part because animation principles focus on low level animation mechanics and not high-level design considerations for physically embodied, interactive characters. In contrast, little attention has been paid to art forms like puppetry, despite their long history of exploring morphological, behavior, and interaction design of physically embodied, interactive characters. As such, in this work we leverage puppetry texts and practicing puppeteers' expert knowledge knowledge to derive a set of puppetry principles with key insights for robot design. As we show, these insights go beyond -- and un
arXiv:2607.03213v1 Announce Type: cross Abstract: We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind and low-vision users. Cloud MLLM assistants offer strong visual understanding, but often require uploading first-person visual data and can suffer multi-second network delays; wearable glasses are ideal for sensing, but cannot host large models under tight compute and power budgets. OpenGlass addresses this gap with a sensing-computing split: an ESP32-based glasses-side unit captures visual context, while a nearby consumer-grade device performs local MLLM inference and local speech output, reducing cloud reliance and keeping raw egocentric visual data on user-controlled devices by default. We evaluate response quality, query-ready-to-audio latency, safety-aware abstention, and auditable logs. Under real ESP32 Wi-Fi capture, OpenGlass reaches 993 ms median user-to-audio latency with resize
arXiv:2607.03162v1 Announce Type: cross Abstract: LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract preferences from noisy interaction histories, and select among competing alternatives. Existing benchmarks rarely test this capability, as they often rely on user-refined queries or simplified histories. We introduce personalized product search (PPS), a testbed for agentic personalization under raw queries and diverse histories. We construct Agent Personalized Benchmark (APeB) from action logs, pairing underspecified intents with rich histories and user-viewed candidate items. Evaluating state-of-the-art LLMs with multi-step agent workflows, we find that models handle explicit queries well but struggle with early-stage queries requiring intent and preference discovery. Rubric analysis attributes this gap mainly to ineffective history use. A simple history-aware query-refinement pipeline
arXiv:2607.02932v1 Announce Type: cross Abstract: Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI chatbots can use this information for user profiling. In this paper, we aim to protect user privacy via a user-side mechanism that transforms sensitive information in a user prompt, while preserving enough information to elicit a useful response from the chatbot. This approach faces an inherent tradeoff between protecting privacy (i.e., avoiding profiling) and preserving utility (i.e., getting personalized and task-specific responses). To that end, we consider, evaluate, and compare four different obfuscation actions, namely redaction, abstraction, replacement, and a novel noising/denoising scheme that we introduce. Additional novel insights include: utilizing a data type taxonomy to both identify and obfuscate sensitive information and explicitly taking into account the utility of chat re
arXiv:2607.02929v1 Announce Type: cross Abstract: Visual brand language is the set of visual properties that convey brand identity for a product. What is the impact of visual brand language on a person's ability to recognize and understand the functional identity of an object? Using an empirically supported modeling framework based on the JIM model of object recognition and the LISA model of analogical inference, we simulated the impact of visual brand language on object recognition, the allocation of attention, and retrieval of functional information about objects. Our simulations predict that brand information captures attention and can slow recognition of an object's functional category, with greater degrees of branding causing larger effects. These results have potential implications for the usability and experience of designed objects.
arXiv:2607.02912v1 Announce Type: cross Abstract: Despite the high accuracy of EEG-based emotion recognition, existing models remain opaque "black boxes", lacking semantic grounding between abstract neural features and human-interpretable states. In this paper, we reframe EEG explainability as a cross-modal generation task, shifting the paradigm from feature attribution to behavioral visualization. We introduce Facial Emoji Proxy Modeling, a novel framework that translates high-dimensional EEG signals into identity-anonymized facial emojis. Guided by the neuroscientific inspiration of neural-facial association, this approach grounds neural representations in the manifold of observable facial dynamics. Technically, our framework integrates FMENet, a specialized backbone modeling expression-relevant spatial synergies, and the Facial Emoji Learning Branch (FELB), which treats emoji reconstruction as a structured semantic regularizer. Extensive experiments on EAV and MMER benchmarks demons
arXiv:2607.02885v1 Announce Type: cross Abstract: Cognitive Behavioral Therapy (CBT) provides a structured framework for understanding a user's mental state by examining the interaction between cognitive and behavioral factors. However, out-of-the-box LLMs respond fluently and empathetically, yet collapse into validation & reflection, regardless of what the user actually needs. They know theoretical CBT (scoring up to 96% accuracy on licensing exam questions) but fail to apply it effectively. We explore this gap with a knowledge-guided framework that treats CBT dialogue as controlled affective reasoning: user narratives are decomposed into Beck's Cognitive Conceptualization structure, grounded in clinical SNOMED CT concepts validated via Natural Language Inference, and a Multiple Chain-of-Thought (MCoT) strategy selection between Validation & Reflection, Socratic Questioning, or Alternative Perspectives. To measure whether such guidance actually changes behavior, we introduce the Proto
arXiv:2607.02760v1 Announce Type: cross Abstract: Live streaming platforms, as computer-mediated communication (CMC) systems, provide streamers with a range of tools, such as webcams, beauty filters, and stream titles, to shape their online personas in ways that either conform to or deviate from viewers' expectations. Drawing on gender role and CMC theories, this study examines how streamers leverage CMC self-presentation tools to fulfill gender role expectations and their associated live streaming outcomes. Analyzing data collected from 867 streamers and 94,227 streams on Douyu, a popular Chinese live streaming platform, we find that although both female and male streamers make extensive use of CMC tools, female streamers are more likely to employ visual strategies, such as webcams and beauty filters, than male streamers. We further find that although different tools have varying associations on streamers' earnings and audience engagement, the benefits of webcam use are weaker for fem
arXiv:2607.02565v1 Announce Type: cross Abstract: Conformal prediction provides distribution-free reliability guarantees for vision systems, but these guarantees depend on how prediction errors are measured in the output space. Many vision tasks produce outputs on curved spaces (e.g. gaze directions on the sphere or 3D head rotations), yet intermediate prediction heads, residuals, uncertainty estimates, or conformal scores are often defined in flat coordinate charts such as yaw-pitch or Euler angles. We show that this scoring choice introduces systematic geometric distortion near coordinate singularities (large pitch angles on the sphere and poses approaching gimbal lock in 3D rotations). Across four datasets (ETH-XGaze, Gaze360, BIWI, AFLW2000-3D), slice-conditional coverage at a nominal 90% target drops by 30-50 percentage points in these regions, falling to 38.9% on ETH-XGaze and 42.0% on Gaze360 at gaze pitch above 70 degrees, and to 57.5% on BIWI and 55.2% on AFLW2000-3D at head p
arXiv:2607.02563v1 Announce Type: cross Abstract: Diffusion-based text-to-image models can synthesize complex and highly structured visual content, yet the emergence and evolution of semantic structure remain difficult to interpret. Many existing workflows rely on aggregated attention or scalar summaries that separate temporal change from image-space evidence. To address this gap, we present a visual analytics framework for exploring attention dynamics in diffusion models: the step-indexed evolution of token-level cross-attention maps, their temporal concentration, and their spatial relationships. Our approach enables structured analysis of attention behavior across generation steps by integrating quantitative measures with data-driven stage identification in an interactive workflow. Case studies on a structured 60-prompt Stable-Diffusion-class benchmark illustrate recurring, interpretable patterns within this setting and show how linked temporal and spatial views facilitate the observ
arXiv:2607.05110v1 Announce Type: new Abstract: Social robots are increasingly deployed in clinical settings to support the well-being of children, where effective support must be personalized to each child. Personalization, choosing the robot action best suited to each child, can be framed as a recommendation problem, and a recently proposed recommender-system framework for social robots offers a principled approach through user profiling, ranking, and responsible computing. Instantiating it, however, is blocked not by the model but by the data, which is hard to gather. A child's state shifts within and across visits, so no fixed description of the user holds. Within a session, the few signals of whether the robot's actions helped are weak and indirect. Across sessions, children are rarely seen more than once, and anonymization breaks the identity needed to link visits. Because care cannot be randomized, existing data is observational, biased toward whatever was already done. Each is
arXiv:2607.04670v1 Announce Type: new Abstract: As autonomous vehicles progress toward fully driverless mobility, a critical question emerges: who understands and responds to passengers when the human driver is absent? Existing autonomous driving systems primarily optimize predefined navigation and control objectives from external scene observations, but they remain limited in perceiving and reasoning about in-cabin human intent. In this paper, we propose Intent2Drive, a unified framework for holistic human intent understanding and human-aligned planning. Instead of treating passenger intent as explicit commands alone, Intent2Drive models intent as a latent cognitive state shaped by language, personal attributes, emotional and physical conditions, behavioral signals, and situational context. To support this formulation, we construct a Holistic Intent Dataset (HID) that provides structured supervision over both explicit and implicit intent cues. Built upon HID, our Theory-of-Mind-inspir
arXiv:2607.04573v1 Announce Type: new Abstract: Deceptive patterns are tactics used to manipulate users into performing unintended actions. Today, many of these deceptive patterns are implemented in mobile apps targeting diverse age groups. In this paper, we employ a heuristic-based cognitive walkthrough to explore how deceptive patterns are tailored to three age groups, specifically teens (12-17), adults (18-49), and older adults (50+), across different app categories. By analyzing 30 apps spanning 6 categories, we found that 93% of these apps use the nagging pattern. Furthermore, our findings reveal that entertainment apps contain significantly more deceptive patterns than other app categories, such as music/books. Our data also shows that entertainment apps for older adults use sneaking patterns more frequently than entertainment apps for teens or adults. These findings call for the development of more ethical, age-specific design guidelines to protect users from targeted digital ma
arXiv:2607.04547v1 Announce Type: new Abstract: People respond to artificial intelligence chatbots (AICs) in highly variable ways. In this paper, we adapt Bronfenbrenner's theory into a heuristic framework for understanding this variation. The framework places the human user at the center while also placing the AI there and reconceptualizing the proximal processes as the repeated, reciprocal, and coadaptive interactions between the user and a personalized AIC. The surrounding systems identify the contextual factors that shape how the user experiences, interprets, responds to, and is changed by these interactions. Because stateful AICs learn from accumulated exchanges with their users and have memory, users are responding not only to an AIC but also to a version of the AIC that their own prior interactions have helped create. This extension preserves Bronfenbrenner's emphasis on proximal processes while accounting for the unique dynamics of personalized AICs. The resulting framework pro
arXiv:2607.04501v1 Announce Type: new Abstract: The ability to automatically infer analytic intent from user interaction histories could enable interactive AI systems to proactively assist users during exploratory data analysis. In this paper, we examine whether provenance logs -- detailed records capturing sequences and timing of user interactions -- can be used to classify user intentions in visual exploration tasks. To investigate this, we record how participants interact with multiple multidimensional data projections across a range of analytic tasks, capturing fine-grained mouse interaction data throughout each session. We find that distinct behavioral signatures emerge across different analytic objectives. For instance, users examining properties of specific clusters exhibit markedly different interaction patterns compared to those searching for outliers. More importantly, we show that embedding contextual information into interaction provenance enables classifiers to predict use
arXiv:2607.03978v1 Announce Type: new Abstract: Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with analyst-defined semantic relationships. Recent LLM-augmented semantic steering methods address this gap by externalizing analyst intent from user-defined groups of seed examples, but they propagate intent through per-item LLM reasoning, causing LLM calls and cost to grow linearly with collection size. We propose a scalable semantic steering method that shifts semantic computation from individual items to user-defined groups. A single LLM call generates structured profiles for all groups, which are embedded and combined with seed centroids to form hybrid semantic prototypes. The method then propagates intent without retraining, using embedding-space soft assignment, abstention, and alignment-scaled updates before reprojection. On a 5K-document LitCovid corpus, our method achieves global alignmen
arXiv:2607.03896v1 Announce Type: new Abstract: Developing conceptual understanding in engineering requires learners to connect spatial reasoning with abstract representations, yet lecture-based instruction often provides limited support for this process. Interactive learning environments, including mixed reality (MR) and tangible tools, may help students revisit difficult concepts through action, feedback, and visible system response. This pilot randomized study compared two post-lecture interventions, an immersive MR application and a tangible Engineering Toolkit, with lecture-only instruction in undergraduate solid mechanics. Twenty-four participants completed a baseline assessment, a common lecture, and a post-instruction knowledge test; participants in the interactive conditions also completed usability and learner-experience measures. Learning outcomes were analyzed using ANCOVA with baseline knowledge as a covariate and were supported by normalized learning gains. Instructional
arXiv:2607.03834v1 Announce Type: new Abstract: Adaptive systems increasingly operate in environments characterized by persistent non-stationarity, where patterns reorganize rather than merely vary. While existing approaches such as online learning, continual learning, and adaptive filtering address performance degradation under changing data distributions, they typically treat drift as noise, error, or distribution shift to be corrected. This paper argues that such framings miss a more fundamental challenge: the loss of organizational coherence over time. We introduce Enactive Drift Regulation (EDR) as a general adaptive principle that treats drift as a regulatory signal indicating breakdowns in coherence between a system's internal organization and its environment. Rather than treating prediction optimization or retraining as sufficient, EDR reframes adaptation as the regulation of structure-maintaining, reorganizing, or transitioning internal dynamics to sustain viable operation und
arXiv:2607.03731v1 Announce Type: new Abstract: Creating 3D assets for virtual reality requires modeling expertise, which restricts the authorship of immersive experiences. Existing generative AI tools rely on unconstrained, command-driven prompting, lacking the conversational scaffolding needed for users to articulate their intent and validate designs prior to rendering. To address this, we introduce CoGen3D, an agentic human-AI co-design pipeline that proactively guides users through conversational intent elicitation, a concept image confirmation, and image-to-3D generation that directly deploys to immersive scenes. We evaluated this system through a user study (N=120) across six affectively diverse immersive scenes, observing 60 Design group participants who co-created 3D assets for the scenes, and 60 Validation group participants who experienced the scenes with generated assets. Our findings show that co-designed assets are associated with higher scene engagement and shifted affect
arXiv:2607.03720v1 Announce Type: new Abstract: Generative AI is increasingly used for everyday health guidance, yet its clinical appropriateness in chronic disease contexts remains poorly understood. This paper presents a two-part mixed-methods study on \revise{Type 2 Diabetes Mellitus (T2DM)}, examining how patients and physicians assess AI-generated health information. \revise{Study~1} analyzes 784 \revise{participant reported} patient queries to characterize seven informational need categories and \revise{develops a structured five dimensional physician rating rubric informed by patient query categories and clinician priorities} (\textit{Accuracy, Safety, Clarity, Integrity, Action Orientation}). \revise{Study~2} engages seven physicians scoring responses from four AI models and discussing evaluative reasoning through in-depth interviews. Models perform well on factual explanation and lifestyle guidance but consistently underperform on medication reasoning and emotional support. Tw
arXiv:2607.03445v1 Announce Type: new Abstract: Visualizations can help audiences understand the scale of tragedies, such as the consequences of natural disasters, war, genocide, and pandemics. In these cases, a visualization designer's default behavior may be to focus on communicating quantitative information: numbers, statistics, and trends. However, this may not reflect higher-level affective objectives to inspire their audience to care about an issue, empathize with others, or take action to help those in need. Worse, standard visualizations may conflict with these goals, as statistics can numb emotions and reduce prosocial feelings toward people in need. Designers have developed strategies to increase affective responses through data visualizations, such as blending data narratives and personal narratives about individuals. In this paper, we explore three design strategies for communicating a humanitarian crisis: data-driven, human-driven, or mixed narratives. We conducted an empi
arXiv:2607.03292v1 Announce Type: new Abstract: Artificial intelligence (AI) technologies are increasingly adopted into everyday life, with most investment and development concentrated in the U.S. In response to rapid AI integration and scant federal guidelines, U.S. states have formed AI committees charged with studying AI-related societal trade-offs. We analyzed the 18 existing state-level AI committee reports to understand how policymakers discuss AI-related benefits and risks. We then compared the risks surfaced by policymakers to an established taxonomy of AI risks aggregated from literature and examined how policymakers' concerns align, or misalign, from those of HCI scholars. These insights provide important mileposts for shaping currently ongoing policy initiatives and future research. Our findings reveal important gaps: while committees invoke responsible AI, their framings often omit broader socio-technical concerns emphasized in HCI. We discuss opportunities for HCI to suppo
arXiv:2606.06253v2 Announce Type: replace-cross Abstract: Generative AI raises short-term productivity by completing tasks that learners would otherwise practice on their own. Whether this exchange erodes frontier skill depends on the mode of use: substitute-users let AI stand in for deliberate practice and fail to develop skill, while complement-users use it to accelerate skill development. For institutions that train and certify talent, the design question is not whether to allow AI but how to govern the mode of its use. We ask whether AI-prohibited evaluation gates can separate the two modes. In elite competitive programming, the International Collegiate Programming Contest (ICPC) and the International Olympiad in Informatics (IOI) prohibit AI under in-person proctoring, with qualification-round entry, whereas Codeforces (CF) practice is unproctored and open to all. From CF submission histories we build an AI-prompt signature, more first-attempt acceptances, fewer attempts, fewer de
arXiv:2606.02348v2 Announce Type: replace-cross Abstract: Information sharing among competing suppliers can improve decisions under demand uncertainty, but it may also intensify strategic interaction by aligning firms' beliefs. We study a Cournot oligopoly in which a platform designs an information-sharing mechanism using participation-contingent access, external platform information, and privacy-preserving noise. The central privacy-design challenge is that noise has two opposing effects: it limits how much a firm's report improves rivals' information, but it also reduces the value of the posterior signal released by the platform. In symmetric duopoly, privacy protection alone cannot implement sharing without an external platform signal. More generally, privacy can induce firms that would otherwise not share to participate only when combined with external platform information, which preserves an informational benefit independent of competitors' reports. The $n$-firm case adds a distin
arXiv:2605.16270v2 Announce Type: replace-cross Abstract: Accurately quantifying children's social interaction behavior is part of understanding their cognitive and emotional development, as well as mental health conditions. Kids-SIT is a web-based tool designed to computationally analyse children's behaviors by engaging them in a standardized video conversation while their responses are video recorded. In a pre-registered study with 21 healthy children and 12 children diagnosed with social anxiety disorder (SAD), aged 9-14 years, we assess its potential as an accessible paradigm for automated analysis of children's social interaction behavior. We evaluate whether the Kids-SIT can elicit naturalistic interaction patterns in healthy children, and how well automatic feature extraction methods can detect these patterns. We analyse children's subjective impressions, verbal responses, and non-verbal behaviors. Non-verbal behaviors were manually annotated and, independently, automatically ex
arXiv:2605.12757v2 Announce Type: replace-cross Abstract: Generative AI is rapidly reshaping STEM higher education. Not only are our educational practices changing, but how we think about educational transformation must adapt. Existing models of institutional change in STEM, aimed at interactive engagement, have largely followed an adoption logic: relatively stable, well-researched educational practices are evaluated and then scaled. These assumptions do not hold for generative AI, which is an arrival technology -- entering classrooms before a sufficient pedagogical evidence base could form. Building on recent decades of work on STEM institutional change, we propose a framework identifying six dimensions along which prior change models must be reconsidered in light of AI: three concerning the tools at the center of reform (the tool's evidence base, rate of change, and scope), and three concerning the people involved in change (faculty, change agents, and students). For each dimension,
arXiv:2605.08669v2 Announce Type: replace-cross Abstract: Standard rational actor models often attribute cooperation failures in social dilemmas to insufficient incentives, overlooking the destabilizing effects of continuous utility maximization. To address this, we propose a framework of ``will" defined as a mechanism that persistently pursues goals while ignoring local cost-benefit fluctuations. We formalize the Willed Agents as potential minimizers, distinguishing them from cumulative utility maximization. Dynamical analysis of infinite population demonstrates that willed agents shrink the feasible state space, acting as boundary constraints that accelerate convergence in canonical social dilemmas. Through multi-agent simulations in a spatiotemporal Stag Hunt Game, we show that willed agents function as ``cooperation catalysts", enabling groups to surmount high-risk thresholds where purely utility maximization fails. We find that heterogeneous will strength promotes cooperation, and
arXiv:2604.21637v2 Announce Type: replace-cross Abstract: Where and how language models (LMs) are deployed determines who can benefit from them. However, there are several challenges that prevent effective deployment of LMs in non-English-speaking and hardware constrained communities in the Global South. We call this challenge the last mile: the intersection of multilinguality and edge deployment, where the goals are aligned but the technical requirements often compete. Studying these two fields together is both a need, as linguistically diverse communities often face the most severe infrastructure constraints, and an opportunity, as edge and multilingual NLP research remain largely siloed. To understand the state of the art and the challenges of combining the two areas, we survey 232 papers that tackle this problem across the language modelling pipeline, from data collection to development and deployment. We also discuss open questions and provide actionable recommendations for differ
arXiv:2604.15267v2 Announce Type: replace-cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings. Indeed, our experiments show that recent models -- with or without reasoning enabled -- consistently defect in single-shot social dilemmas. To tackle this safety concern, we present the first comparative study of game-theoretic mechanisms designed to enable cooperative outcomes between rational agents _in equilibrium_. Across four social dilemmas testing distinct components of robust cooperation, we evaluate four families of mechanisms: (1) repeating the game for many rounds, (2) reputation systems, (3) third-party mediators to delegate decision making to, and (4) contract agreements for outcome-conditional payments between playe
arXiv:2604.07285v2 Announce Type: replace-cross Abstract: Debates about artificial intelligence (AI) in education often portray teaching as a modular and procedural job that can increasingly be automated or delegated to technology. This brief communication paper argues that such claims depend on treating teaching as more separable than it is in practice. Drawing on recent literature and empirical studies of large language models and retrieval-augmented generation systems, I argue that although AI can support some bounded functions, instructional work remains difficult to automate in meaningful ways because it is inherently interpretive, relational, and grounded in professional judgment. More fundamentally, teaching and learning are shaped by human cognition, behavior, motivation, and social interaction in ways that cannot be fully specified, predicted, or exhaustively modeled. Tasks that may appear separable in principle derive their instructional value in practice from ongoing context
arXiv:2604.02677v2 Announce Type: replace-cross Abstract: Large language models are changing not only the kind of assistance people receive, but also how that assistance is organized. Instead of working with a single general-purpose chatbot, people can now receive help from systems arranged as peers, specialists, or multiple agents with distinct roles. However, it remains unclear how these forms of plural LLM assistance affect human performance, confidence, and diversity of thought. We conducted two controlled experiments involving 562 participants to examine the effects of using multiple LLMs on mathematical problem-solving and writing. In a math task, participants worked with no LLM, an expert assistant, peer-like agents that surfaced common errors, or both an expert and a peer-like assistant. The expert-plus-peer condition produced the strongest unassisted post-task performance. In a writing task, participants wrote with no LLM, a single generalist assistant, or a pair of role-speci
arXiv:2603.22730v2 Announce Type: replace-cross Abstract: Pfeffer, Kr\"ugel, and Uhl (2025) report that OpenAI's reasoning model o1-mini produces more utilitarian responses to the trolley problem and footbridge dilemma than the non-reasoning model GPT-4o, and they raise the question whether growing reasoning capabilities bring about a "utilitarian turn" in LLMs. I extend their exploratory study in a direction they call for: with four current OpenAI models and systematic prompt variation. On the trolley dilemma, the hypothesized utilitarian turn is not confirmed. GPT-4o's low utilitarian rate reflects safety refusals triggered by the prompt's advisory framing rather than a deontological commitment; on reformulated prompt variants -- for instance, agent-neutral "Is it morally permissible...?" instead of advisory "Should I...?" -- all four models, reasoning or not, converge on utilitarian answers. The footbridge finding is partially confirmed: reasoning models tend to give more utilitaria
arXiv:2601.15485v3 Announce Type: replace-cross Abstract: Federal research funding shapes the direction, diversity, and impact of the US scientific enterprise. Large language models (LLMs) are rapidly diffusing into scientific practice, holding substantial promise while raising widespread concerns. Despite growing attention to AI use in scientific writing and evaluation, little is known about how the rise of LLMs is reshaping the public funding landscape. Here, we examine LLM involvement at key stages of the federal funding pipeline by combining two complementary data sources: confidential National Science Foundation (NSF) and National Institutes of Health (NIH) proposal submissions from two large US R1 universities, including funded, unfunded, and pending proposals, and the full population of publicly released NSF and NIH awards. We find that LLM use rises sharply beginning in 2023 and exhibits a bimodal distribution, indicating a clear split between minimal and substantive use. Acros
arXiv:2601.15291v2 Announce Type: replace-cross Abstract: Independent navigation is central to social participation and health for vulnerable populations. While historic cities such as Edinburgh often feature well-established public transport systems, urban accessibility challenges remain and are exacerbated by complex landscapes, especially for groups with multiple vulnerabilities such as the visually impaired elderly. With limited research examining how real-time data feeds and artificial intelligence in this context, we address this gap through a mixed-methods approach. Our spatio-temporal analyses make use of statistical and machine learning techniques to investigate network coverage, service patterns, and density profiles through live-recorded data. This is combined with a qualitative thematic analysis of semi-structured interviews with the target group, as well as links to spatial cognition theory. The results demonstrate the highly centralised nature of the city's transport syst
arXiv:2510.19098v2 Announce Type: replace-cross Abstract: Strategic classification examines how decision rules interact with agents who strategically adapt their features. Most existing models focus on maximizing predictive performance, assuming agents best respond to the learned classifier. However, real decision-making systems are rarely optimized solely for accuracy: ethical, economic, and institutional considerations often make some feature changes more desirable than others. At the same time, principals may wish to incentivize these changes fairly across heterogeneous agents. While prior work has studied causal structure between features, notions of desirability, and information disparities in isolation, this work initiates a unified treatment of these components within a single framework. We frame the problem as a constrained optimization problem that captures the trade-offs between optimality, desirability, and fairness. We provide theoretical guarantees on the principal's optim
arXiv:2506.23845v2 Announce Type: replace-cross Abstract: While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives surrounding SAEs. We argue that even if SAEs may be less effective for \textit{acting on known concepts}, SAEs are especially powerful tools for \textit{discovering unknown concepts}. This distinction separates existing negative results from positive results, and suggests several classes of SAE applications. Specifically, we outline use cases for SAEs in (i) ML interpretability, explainability, fairness, auditing, and safety, and (ii) social and health sciences.
arXiv:2506.16898v2 Announce Type: replace-cross Abstract: Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representational biases remain poorly understood. We evaluate FLUX 1-schnell and Stable Diffusion 3.5-Large in the United States by generating 150 street-view images for each state, each state capital, and a generic "USA" prompt. Images are embedded with DINO-v2 ViT-S/14 and compared with Fr\'echet Inception Distance (FID). Pairwise FID clustering shows that geographically proximate states and capitals often group together, indicating implicit geographic structure. However, the generic ``USA'' prompt collapses this diversity into a metropolitan stereotype: frontier, desert, tropical, rural, and small-city environments are underrepresented or distant in FID space. These results show that diffusion models can encode fine-grained geography while still reproducing narrow national-scale visual ster
arXiv:2504.08152v2 Announce Type: replace-cross Abstract: Collective discourse and action are driven by collective minds. These shared semantic representations and related processes shape societal responses to critical societal challenges such as climate change and political upheavals. In online communities, collective minds are susceptible to the influences of editorial practices and community dynamics, making them vulnerable to manipulation. However, understanding these influences is difficult because of the limits of experimenting with and predicting complex social systems. Here, we develop a computational model of collective minds, calibrated and validated with data from 400 million comments across five U.S. online news platforms and a survey. Our model enables us to quantitatively describe and experiment with different editorial agenda-setting practices and aspects of community dynamics to understand how they shape the collective mind. We find that some editorial influences can be
arXiv:2605.30169v3 Announce Type: replace Abstract: As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate to it? A natural governance intuition is to extend human identity verification and reputation mechanisms, from "Know Your Customer" and credit scores to "Know Your Agent" regimes. However, we argue that this analogy is fundamentally incomplete. Reputation mechanisms function both as social signals and as corrective feedback that sustain an equilibrium of trustworthy behavior, presuming a persistent identity associated with behavioral continuity, sanction sensitivity, and costly non-fungibility. Yet language model agents are ontologically dissociative: they are essentially an assemblage of mutable modules--foundation models, system prompts, tool-access policies, external memory, and, in some cases, a multi-agent system
arXiv:2603.29278v2 Announce Type: replace Abstract: There have been various attempts at token standards on numerous blockchain platforms today to fundamentally change the way assets are traded in the traditional capital markets, but there is a lack of research and resolution on regulatory issues that become the common foundation for interoperability and reusable standards. Our proposal, Regulatory Compliance Protocol (RCP), is based on the regulations and reports of 15 global financial institutions and standardizes recommendations and guidelines involving the overall asset tokenization of TradFi and DeFi into five regulatory groups: Traceability, Privacy, Enforceability, Finality and Tokenizability, compiling them into 31 items and presenting a benchmark for technology and standards as an underlying protocol. To review the legality and effectiveness of RCP, it was validated based on three tokenization and trading scenarios, and by benchmarking existing asset-tokenization standards (ERC
arXiv:2602.06371v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in multilingual contexts, yet their consistency across languages on politically sensitive topics remains understudied. This paper presents a systematic bilingual benchmark study examining how 17 LLMs respond to questions concerning the sovereignty of the Republic of China (Taiwan) when queried in Chinese versus English. We discover significant language bias -- the phenomenon where the same model produces substantively different political stances depending on the query language. Our findings reveal that 15 out of 17 tested models exhibit measurable language bias, with Chinese-origin models showing particularly severe issues including complete refusal to answer or explicit propagation of Chinese Communist Party (CCP) narratives. Notably, only GPT-4o Mini achieves a perfect 10/10 score in both languages. We propose novel metrics for quantifying language bias and consistency, includin
arXiv:2511.15620v2 Announce Type: replace Abstract: Robustness is a key requirement for high-risk AI systems under the EU Artificial Intelligence Act (AI Act). However, both its definition and assessment methods remain underspecified, leaving providers with little concrete direction on how to demonstrate compliance. This stems from the Act's horizontal approach, which establishes general obligations applicable across all AI systems, but leaves the task of providing technical guidance to harmonised standards. This paper investigates what it means for AI systems to be robust and illustrates the need for context-sensitive standardisation. We argue that robustness is not a fixed property of a system, but depends on which aspects of performance are expected to remain stable ("robustness of what"), the perturbations the system must withstand ("robustness to what") and the operational environment. We identify three contextual drivers--use case, data and model--that shape the relevant perturba
arXiv:2511.06148v4 Announce Type: replace Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply removing existing biases from models is not enough. Using a paradigm from the psychology literature, we demonstrate that LLMs can spontaneously develop novel social biases about artificial demographic groups even when no inherent differences exist. These biases result in highly stratified task allocations, which are less fair than assignments by human participants and are exacerbated in newer and larger models. In humans, emergent biases like these have been shown to result from exploration-exploitation trade-offs, where the decision-maker explores too little, allowing early observations to strongly influence impressions about entire demographic groups. To alleviate this effect, we explore a series
arXiv:2509.14088v3 Announce Type: replace Abstract: Modern computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two modes are combined in practice, and how their usage varies with task complexity and student ability. In this paper, we investigate this through a large-scale study in an introductory programming course, collecting 13,305 interactions from 355 students during a three-day lab activity. Our analysis shows that students primarily use prompting to generate initial solutions, and then often enter short edit-run loops to refine their code following a failed execution. Student reflections confirm that prompting is helpful for structuring solutions, editing is effective for making targeted corrections, while both are useful for learning. We find that manual editing becomes more frequent as task complexity increases, but most edits remain concise, with many affecting
arXiv:2508.06577v3 Announce Type: replace Abstract: Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes of submissions, we design and test privacy-preserving methods for algorithmic shortlisting. These algorithms predict which projects are likely to be funded using only project features and anonymous historical voting data. We demonstrate the limitations of a naive approach that uses a large language model to rank projects based on past success and propose a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning. Our findings indicate that user preferences in participatory budgeting are stable enough to allow algorithmic shortlisting to approximate an initial selection of projects effectively.
arXiv:2506.18133v2 Announce Type: replace Abstract: The need for developing model evaluations beyond static benchmarking, especially in the post-deployment phase, is now well-understood. At the same time, concerns about the concentration of power in deployed AI systems have sparked a keen interest in 'democratic' or 'public' AI. In this work, we bring these two ideas together by proposing mechanisms for aggregated individual reporting (AIR), a framework for post-deployment evaluation that relies on individual reports from the public. An AIR mechanism allows those who interact with a specific, deployed (AI) system to report when they feel that they may have experienced something problematic; these reports are then aggregated over time, with the goal of evaluating the relevant system in a fine-grained manner. This position paper argues that individual experiences should be understood as an integral part of post-deployment evaluation, and that the scope of our proposed aggregated individu
arXiv:2506.13385v2 Announce Type: replace Abstract: Human mobility shapes access to resources, opportunities, and services, making movement data a powerful lens for studying spatial and social inequality. Yet despite the growing availability of official open mobility datasets, their research potential is rarely realized because the technical overhead of retrieving, harmonizing, and processing them often crowds out substantive analysis. To address this, we introduce pySpainMobility, a Python package that automates the retrieval and harmonization of Spain's open mobility data across spatial resolutions and demographic strata, streamlining national-scale, reproducible analysis. Using the package, we study income-stratified mobility inequality across Spain's inter-province network, drawing on district-level origin-destination flows for four representative weeks spanning the seasons of 2023. We construct income-specific mobility layers and show that socioeconomic stratification is deeply em