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:2609.03678v1 Announce Type: new Abstract: We propose a conceptual framework for exploratory data analysis of (large) unstructured data (EluDA), combining classical elements (querying, visualization) with active knowledge construction in the "search for structure". In a formative study, users conceptualized a structure for an image dataset during exploration. We found that users conceptualize by building faceted classifications bottom-up and rarely create meaningful spatial categorization during this process. We also evaluated CLIP for zero-shot assignment and semantic categorization, finding that it remains unreliable for assigning user-defined concepts to images but does support semantic grouping. Based on these findings, we identify and discuss four key opportunities for human-AI collaboration in EluDA: intelligent sampling and visualization to maximize data visibility; incremental and few-shot learning to minimize effort for reliable assignment; automatic category, concept, an
arXiv:2609.03665v1 Announce Type: new Abstract: As XR matures into a ubiquitous computing platform, the disconnect between 2D and 3D input modalities remains a critical barrier to seamless workflow. Frequent transitions between the mouse for 2D precision and hand gestures for 3D manipulation induce significant physical fatigue and cognitive load. To address this, we introduce PlanePivoting, a multimodal interaction technique that extends standard mouse input into 3D space by leveraging gaze-mouse alignment. This technique dynamically modulates the translation plane based on the spatial overlap between the gaze and mouse cursor, eliminating the need for physical input modality switching. To systematically explore the foundational design space of gaze-mouse coordination and optimize key variables, we conducted a user study comparing PlanePivoting with a standard 3D Gizmo interface across two translation mapping profiles and two gaze cursor apertures. Results demonstrate that PlanePivotin
arXiv:2609.03661v1 Announce Type: new Abstract: Mid-air object instantiation in XR requires users to specify a 3D position without spatial references, such as surfaces or existing objects. We present Point&Spawn, a staged pipeline for pre-instantiation position specification through Direction Setting, Depth Setting, and Position Refinement within a continuous gesture flow. We evaluated six controller-free techniques combining Gaze or Non-Dominant Hand (NDH) direction setting with Ray Intersection, Relative Gain, or Drag&Hold depth setting in a user study (N=24) across Near and Far spawn depths. Relative Gain and Drag&Hold yielded faster and more accurate spawning, lower workload, higher usability, and greater preference than Ray Intersection. The shoulder-referenced NDH ray improved speed and coarse accuracy, whereas the viewpoint-based Gaze ray reduced hand movement with comparable final accuracy. Farther spawn depth imposed greater temporal costs as well as Gaze and accuracy costs wi
arXiv:2609.03295v1 Announce Type: new Abstract: Emergency Department (ED) teams coordinate shifting roles, medication decisions, and time-critical interventions under uncertainty. Augmented reality head-mounted displays (AR-HMDs) have shown potential to spatially anchor information during care, creating opportunities to examine how spatial interfaces might support teamwork. We conducted a speculative co-design study with 12 healthcare workers (HCWs) using an editable, desktop-mediated Unity-based 3D design probe to visualize and refine work-as-imagined AR-HMD interfaces for role-based notifications, task-specific timers, and dosage verification. Guided by microinteraction rules, participants identified future spatial user interfaces (SUI) requirements such as how they appear, update, or are dismissed in relation to clinical practice, safety concerns, and existing tools. Five returning participants and 26 additional HCWs subsequently provided follow-up feedback on derived visual interfa
arXiv:2609.03169v1 Announce Type: new Abstract: Pervasive games extend the magic circle across spatial, temporal, and social dimensions, yet treat the player's physiological and cognitive state as a passive receptor rather than an active signal. This paper presents LifeSync-Games (LSG), a framework that (unlike proposals treating player signals as an additional dimension), operationalizes them as a Player Experience Integration Layer (PEIL) acting transversally across the three existing pervasive dimensions through verified real-world signals: physical activity, sleep quality, memory, and decision speed. The framework introduces a gamified integration artifact (the LSG portal) that mediates the real <-> virtual exchange through redeemable points, real-world missions, and structural gamification. Five HCI design principles grounded in Self-Determination Theory and Flow Theory are proposed, instantiated across six commercial video games, together with a study protocol (n = 70-80 particip
arXiv:2605.28025v2 Announce Type: replace-cross Abstract: Existing safety evaluations for large language models overlook whether responses preserve comparable medical information across different user phrasings of the same question. To address this, we introduce the Medical Information Response Audit (MIRA), a bilingual, controlled benchmark that assesses whether LLMs provide comparable medical information across user-side language, register, and health literacy signals. MIRA contains 4,320 prompts built from 60 medically reviewed, low-risk health questions. Across five mainstream LLMs, models answered all medical questions, but responses to low health-literacy signals consistently omitted more key information, provided fewer concrete next steps, and offered less support for independent judgment. We term this pattern Differential Information Dilution (DID). A comparison with 300 real-world health queries provides preliminary evidence of rank-order validity. A knowledge-guided mitigatio
arXiv:2605.13706v2 Announce Type: replace-cross Abstract: From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models (LLMs). However, large-scale web scraping to feed LLMs can affect site stability and raise legal, privacy, or ethics concerns. If website owners wish to limit LLM-related web scraping on their site, due to these or other concerns, they may turn to scraper access control mechanisms like the Robots Exclusion Protocol. To be most effective, such mechanisms require site owners to first identify the scrapers that they wish to restrict (e.g., via User-Agent strings). Existing mechanisms to identify LLM-related scrapers rely on voluntary disclosure by companies, one-off experiments by researchers, or crowd-sourced reports -- methods that are neither reliable nor scalable. This paper proposes a novel technique for accurately and automatically inferring LLM-related scrapers. We
arXiv:2605.12462v2 Announce Type: replace-cross Abstract: Extreme weather and volatile wholesale electricity markets expose residential consumers to catastrophic financial risks, yet demand response at the distribution level remains an underutilized tool for grid flexibility and energy affordability. While a demand-response program can shield consumers by issuing financial credits during high-price periods, optimizing this sequential decision-making process presents a unique challenge for reinforcement learning despite the plentiful offline historical smart meter and wholesale pricing data available publicly. Offline historical data fails to capture the dynamic, interactive feedback loop between an electric utility's pricing signals and customer acceptance and adaptation to a demand-response program. To address this, we introduce DR-Gym, an open-source, online Gymnasium-compatible environment designed to train and evaluate demand-response from the electric utility's perspective. Unlike
arXiv:2510.16046v4 Announce Type: replace-cross Abstract: We present CARDIO-Affect, a complex-systems theoretical framework for long-term emotional dynamics in bounded social groups, with explicit uncertainty quantification at every layer. Long-period naturalistic emotion in stable small groups exhibits hallmarks of complex systems -- multi-stable attractors, weak chaos, long-range memory, and sparse heterogeneous coupling -- invisible to conventional short-clip facial-emotion analysis. CARDIO-Affect treats individual emotion as a multi-stable nonlinear stochastic dynamical system and group emotion as a sparsely-coupled network with emergent macrostates, formalised through six propositions and four pillars: (i) statistical mechanics with neural-parameterised Hamiltonian SDE over asymmetric potentials; (ii) information geometry on a 45-dimensional Fisher-Rao manifold; (iii) topological data analysis for invariant trajectory signatures; (iv) HRV-inspired Emotional Variability Analytics (
arXiv:2510.15221v3 Announce Type: replace-cross Abstract: Affective computing has matured rapidly in laboratory settings, yet no prior dataset combines (i) months-to-years of duration, (ii) a naturalistic workplace context, (iii) a stable small-team social structure, and (iv) a fully passive sensing protocol that survives institutional review. We introduce WELD, the first dataset to satisfy all four. WELD comprises 733,780 per-frame seven-class facial-expression probability vectors from 49 employees of a Chinese software company over 30.1 months (Nov 2021 - May 2024) -- the longest naturalistic in-the-wild emotion corpus and the only multi-year corpus supporting both within-individual longitudinal and within-team relational analyses on the same subjects. Data are released under a four-tier access model with only aggregated probabilities publicly downloadable. We validate the corpus by replicating three established phenomena (+43.1% weekend valence boost; 13:00-trough diurnal cycle; Sha
arXiv:2604.00945v2 Announce Type: replace Abstract: Vibe researching is an emerging paradigm in which human researchers provide high-level direction and critical judgment while LLM-based agents handle the labor-intensive execution of literature review, experimentation, data analysis, and manuscript drafting. Inspired by the "vibe coding" movement in software engineering, it occupies a middle ground between traditional manual research and fully autonomous AI research systems. This paper defines the concept, describes its methodology (multi-agent architectures, memory, tool use, retrieval-augmented generation, and the human's role as orchestrator), identifies seven technical limitations, weighs its positive and negative societal impacts, and maps each problem to a concrete future direction. Our goal is to provide the research community with a clear and honest map of the territory so that the conversation about responsible adoption can start from shared ground.
arXiv:2609.03770v1 Announce Type: cross Abstract: Institutions practising outcome-based education compute learning outcome attainment routinely, while reviews of curriculum analytics report an absence of evidence on how that computation informs decisions. This paper presents OBER+, an extension of a deployed institutional attainment platform that computes the step from a measured shortfall to an evaluated corrective action. Five connected stages accumulate attainment across deliveries of a course, signal a shortfall and a persistent shortfall, grade it on cutoffs the regulator already uses, record the decision against a catalogue of practices annotated with their evidence, log the change, and quantify the subsequent movement in the shortfall. A further rule compares successive statements of an outcome, so attainment is never read as a series across a point at which the outcome changed. Applying the rules to the live record of two real courses produced three results. Every outcome of a
arXiv:2609.03553v1 Announce Type: cross Abstract: Policy analysis requires more than predicting whether a proposal will pass: it requires identifying who will be affected, how those actors respond, and what follows. LLM-based policy simulations model these processes at scale, but their validity is hard to establish when plausible behaviour is never compared with observed outcomes. We introduce GPS-Bench, an evidence-grounded benchmark for governance policy simulation that links policies to relevant actors, actor actions and downstream impacts using legislative records, lobbying disclosures, regulatory documents, corporate filings, economic data and other public evidence. Actors are reconstructed from the dated record rather than prompted as archetypes, so a persona is an evidence object with provenance; a human-annotated pool forms the Gold evaluation set, while cases labelled by a separate LLM from retrieved evidence are treated as Silver supervision and never as test labels. Because
arXiv:2609.03366v1 Announce Type: cross Abstract: Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision. We examine accountable AI through clinical trial matching, a high-stakes task central to evidence-based medicine. Although LLM-based matchers match patients to trials reasonably accurately, they apply decision policies inconsistently and produce rationales that are unfaithful to their own decisions. We introduce VERDICT, an LLM-based agent that translates a decision task, its constrai
arXiv:2609.03344v1 Announce Type: cross Abstract: Large-language models (LLMs) are rapidly becoming part of human culture, reshaping how information is produced, transmitted, and used. Here we propose that their diffusion can be understood through a viral analogy, with LLM use spreading through populations, becoming embedded in cognitive and cultural practices. We model transitions among uncoupled, coupled, and persistently dependent users, and show that the interplay between social transmission, recovery, and collective reinforcement can generate tipping points and technological lock-in. A central consequence is the possibility of runaway dynamics: once a critical threshold is crossed, small increases in adoption can trigger rapid population-level shifts toward persistent dependence, with abrupt losses in cognitive competence. The same framework, however, identifies conditions for cognitive immunization, based on reducing transmission and facilitating reversibility. Our results highli
arXiv:2609.03330v1 Announce Type: cross Abstract: Moral language plays a central role in shaping online endorsement and the diffusion of information, yet existing moral foundation detection systems often suffer from poor cross-domain generalization, weak rationale grounding, and reliance on costly prompting-based large language models (LLMs). We introduce CHARM, a MA\textbf{C}- and \textbf{H}ate-speech-\textbf{A}ware \textbf{R}ationale-aligned \textbf{M}oral foundation detection framework built on a lightweight fine-tuned LLM, which integrates complementary moral grounding, rationale alignment, and polarity-aware hate speech signals to support more robust and faithful moral prediction. Unlike prior dictionary-, fine-tune-, or prompt-based detectors, which decouple computation from psychological theory, CHARM is built so that each component -- MAC cross-attention, rationale alignment, and hate-speech modulation -- operationalizes a distinct psychological construct. Using a 30\% subsampl
arXiv:2609.02920v1 Announce Type: cross Abstract: As the music industry becomes an increasingly collaborative effort, understanding the underlying structures of the artist network has become a focal point in cultural data analytics. This study expands on the previous analyses of the Italian and Danish networks by introducing a novel dataset of the Polish music scene. By utilizing methodologies used in the prior studies, this work enables a direct comparison between three distinct European music landscapes and allows to merged the created networks into one. Furthermore, this research introduces a framework to test the efficacy of Graph Neural Networks (GNNs) for artist popularity predictions based on the metadata and the position in the network. The statistical analysis revealed that the Polish and tri-national network exhibit similar properties and clustering behaviours, consistent with prior models. An evaluation of the predictive architectures reveals that while GNN models achieve a
arXiv:2609.04125v1 Announce Type: new Abstract: The proliferation of digital tools in education offers numerous benefits but also introduces significant challenges, notably digital distractions that hinder academic performance, especially in online learning contexts. This study employed unsupervised data mining techniques, specifically association rule mining and clustering analysis, to identify effective learning strategies associated with lower levels of digital distractions among college students. Data from 530 participants revealed that self-regulated learning strategies (i.e., goal setting, environment structuring, and time management) co-occurred most consistently with lower digital distractions. Additionally, learner-instructor and learner-content engagement strategies, as well as technical competencies, also tended to appear in the same profiles as lower distraction. Interestingly, reliance on peer help-seeking and learner-learner engagement strategies appeared less often in th
arXiv:2609.03999v1 Announce Type: new Abstract: Large language models (LLMs) are becoming integral to web applications and browser agents, transforming online interactions while introducing new attack vectors and reshaping longstanding web vulnerabilities. Classical threats such as cross-site scripting (XSS) can be amplified through LLM-mediated interactions, while LLM-specific vulnerabilities can propagate across web applications, introducing attacks such as prompt injection. Securing modern web systems therefore requires understanding interactions between traditional and LLM-specific threats across the system lifecycle. Unlike prior surveys treating web and LLM security separately, this survey provides a unified analysis of how LLMs amplify web vulnerabilities across client-side, server-side, and pipeline layers while evaluating defenses and their limitations. The analysis examines extending NIST and ISO/IEC AI security frameworks to the security needs of LLM-enabled web environments
arXiv:2609.03936v1 Announce Type: new Abstract: The persistent gender imbalance in computing remains a global concern, and universities offer a key part of the pipeline to address it. Although research has identified practices that support under-represented student groups, translating this evidence into actionable guidance remains challenging. This paper first presents a novel web- based toolkit (TechMate) designed to address this gap by helping computing educators implement gender- inclusive initiatives through practical research-informed guidance. The toolkit defines over 25 actions, ranging from operational to strategic, and provides case studies and implementation resources. Second, this work reports on the evaluation of TechMate, capturing educators first impressions of its usefulness and usability through authentic tasks, and eliciting unanticipated insights about structural barriers to gender-inclusive practice in computing higher education. Eighteen computing educators of varyi
arXiv:2609.03853v1 Announce Type: new Abstract: While fairness has become a central concern in research on algorithmic systems, the field remains predominantly shaped by Computer Science, resulting in a strong emphasis on formal fairness metrics and bias mitigation strategies. Nevertheless, this focus may obscure a fundamental challenge: fairness is not merely a technical property, but a subjective, context-sensitive human judgment shaped by cognitive heuristics, mental models, normative expectations, and sociotechnical factors. Crucially, users' perceptions of fairness may diverge substantially from the fairness criteria an algorithm formally satisfies; a system may meet predefined technical fairness requirements yet still be perceived as unjust by decision-affected stakeholders. In such cases, the system fails on a fundamental dimension: it will not be trusted, accepted, or considered legitimate. Taking a user-centered design perspective, this paper presents a work-in-progress concep
arXiv:2609.03666v1 Announce Type: new Abstract: The Metaverse is often framed as a persistent, interoperable, and embodied network of virtual and augmented environments. Yet, most contemporary XR applications are developed through commercial game engines and distributed through proprietary app stores, creating tensions between openness and platform dependency. This paper critically examines open WebXR technologies with conventional commercial game-engine pipelines, with particular attention to XR hardware, software architectures, developer workflows, governance, ethics, and sustainability. We argue that WebXR may provide a viable route toward a more accessible, device-independent, and institutionally sustainable Metaverse, especially for education, research, cultural heritage, prototyping, and public-interest applications. At the same time, commercial engines remain advantageous for graphically intensive, low-latency, deeply integrated, and large-scale XR products. The paper concludes
arXiv:2609.03413v1 Announce Type: new Abstract: Contributions: A reflection model suitable for the era of Generative Artificial Intelligence (GenAI) is introduced. The proposed model is an integrated model that extracts features from various existing models and also incorporates technological aspects of GenAI. Background: Universities worldwide are facing challenges in adopting GenAI into their curricula, as it has impacted academic integrity and the scholarship of teaching and research. Traditional reflection models are struggling to authenticate student reflection as GenAI is incorporated in education. This requires a GenAI-aware model to enable the opportunities that address the associated challenges with GenAI. Research Questions: Does the academic ecosystem require a GenAI-aware reflection model to adopt GenAI into education? How to make a reflection model structured to ensure student authenticity and cognitive engagement within a GenAI-aware learning environment? Methodology: Thi
arXiv:2609.03301v1 Announce Type: new Abstract: Wildfire seasons have become 84 days longer in the current days than in the 1970s, causing enormous threats to one's financial status and short- and long-term health. During the fire, public agencies send out emergency messages to provide warnings and orders. Although 26 million people in the US have limited English proficiency, over 80% of those messages are only delivered in English, which can cause disproportionate information distribution and awareness. In order to better serve marginalized communities during emergencies, the authors developed BEACON, a service that provides comprehensive and personalized evacuation guidance, including navigation routes, personalized checklists, and a chatbot in the language that a user uses. Our current system ingests data including fire perimeter information, evacuation order status, and shelter information from Watch Duty. When a user is within a certain proximity from the fire, the system utilizes
arXiv:2609.03269v1 Announce Type: new Abstract: What is the emotional register of Arabic YouTube's affective publics? To investigate this, we analyzed 67,725 YouTube comments collected around socio-political topics associated with Yemen, Saudi Arabia, Iraq, Jordan, and Syria using a unified sentiment-and-emotion pipeline. Our results profile a single regional affective public rather than five separate national ones. Sentiment is overwhelmingly negative across all five country-oriented corpora, and the country-level emotion profiles are structurally similar. This shared register still accommodates some regional variations: discourse is organized around country-level political actors and cross-border historical trauma figures, and grief singularizes Iraq from the other countries. The differences in emotional register also tracks lived political causes rather than fixed categories, which we observe from patterns of the valence of US-related content, that tracks the presence or absence of
arXiv:2609.03189v1 Announce Type: new Abstract: This article presents a structured framework of behavioral indicators that may signal progression toward potentially catastrophic threats from artificial intelligence systems. We adopt a pragmatic approach, inspired by established methodologies in cybersecurity and national security. By establishing clear metrics, indicators, and thresholds across multiple dimensions of AI capability and behavior, this framework enables researchers and policymakers to implement evidence-based monitoring protocols.
arXiv:2609.03178v1 Announce Type: new Abstract: We investigate the design of robust risk models to assess societal risks posed by advanced AI systems, an emerging area in AI governance. Many regulatory proposals increasingly require systemic risk assessment, but in the absence of rigorous quantitative methods, the question remains what state of the art risk modeling should look like in practice. We identify the key methodological and institutional challenges that currently limit the adoption of risk modeling. We review five research traditions that inform this problem: probabilistic risk assessment, catastrophic AI risk analysis, cybersecurity risk quantification, Bayesian causal inference, and threshold-based governance. We compare two leading proposals, scenario-based risk estimation and Bayesian network-based threshold setting. Drawing on a workshop with 22 experts and subsequent analysis, we identify a structured agenda of open questions concerning model structure, scope, evidence
Universities are attempting to adapt to artificial intelligence while considering mostly the wrong questions. The post Before students use AI, they should prove they don’t need it appeared first on eCampus News .
arXiv:2606.22737v2 Announce Type: replace-cross Abstract: Before letting an agent operate over real context, can you prove it used the right evidence? GroundEval turns that question into a deterministic test of what the agent searched, fetched, cited, and was permitted to access. In one case study, two frontier LLM judges scored a plausible agent response 0.85 and higher. But the trace told a different story: the agent had never retrieved the artifact its answer depended on, yielding a GroundEval score of 0.000. We introduce GroundEval, a judge-free framework for evaluating agents against grounded, time-bounded, and access-controlled evidence. GroundEval uses a domain configuration to generate questions, lets the agent choose how to answer, and then scores both the final answer and the recorded trajectory that produced it. The benchmark targets three failures that LLM-as-judge evaluation struggles to detect: whether an agent checked before claiming absence, reasoned only from evidence
arXiv:2606.07591v4 Announce Type: replace-cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7,
arXiv:2605.17450v2 Announce Type: replace-cross Abstract: As software systems grow increasingly complex, automated vulnerability repair (AVR) remains difficult because the materials available to a repair system are usually failure artifacts rather than repair guidance. Traditional analysis techniques can provide suspicious locations, reduced triggers, or constraints, but they are costly to configure across repositories and seldom directly actionable for patch generation. Recent LLM-based agents can edit and validate repository-level patches, and experience-based systems can reuse prior repair traces or demonstrations, but they still need current-instance evidence that turns a broad, symptom-level failure report into a concrete repair decision. We present ContraFix, an agentic AVR framework that constructs such evidence through contrastive runtime analysis. Starting from a failing witness, ContraFix generates nearby failing and non-failing variants, executes them through aligned probe s
arXiv:2604.26180v2 Announce Type: replace-cross Abstract: With recent semantic query processing engines, semantic aggregation has become a primitive operator, enabling the reduction of a relation into a natural language aggregate using an LLM. However, the resulting semantic aggregate may contain claims that are not grounded in the underlying relation. Verifying such claims is challenging: they often involve quantifiers, groupings, and comparisons over relations that far exceed LLM context windows and require a costly combination of semantic and symbolic processing. We present Evergreen, a system that recasts claim verification as a semantic query processing task with tailored optimizations and provenance capture. Evergreen compiles each claim into a declarative semantic verification query that can execute on the same query engine used to produce the aggregate. To reduce cost, Evergreen avoids unnecessary LLM calls through verification-aware optimizations, including early stopping, rel
arXiv:2604.21254v3 Announce Type: replace-cross Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model's memory footprint, thus motivating parameter-efficient architectures for language modeling. This paper describes a simple architecture that improves the parameter-efficiency of LLMs. Our architecture makes use of looped Transformers as a core primitive, which reuse Transformer layers across depth and are thus more parameter-efficient than ordinary (depth-matched) Transformers. We organize the looped Transformer into three blocks--begin, middle, and end blocks--where each block itself consists of multiple Transformer layers, and only the middle block is applied recurrently across depth. We augment the looped middle block with hyper-connections (Xie et al., 2026), which expand the residual stream into matrix-va
arXiv:2604.19775v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capability to perform multi-step reasoning and decision-making tasks, internal mechanisms guiding their sequential behavior remain opaque. This paper presents a framework for interpreting the temporal evolution of concepts in LLM agents through a step-wise conformal lens. We introduce the conformal interpretability framework for temporal tasks, which combines step-wise reward modeling with conformal prediction to statistically label model's internal representation at each step as successful or failing. Linear probes are then trained on these representations to identify directions of temporal concepts - latent directions in the model's activation space that correspond to consistent notions of success, failure or reasoning drift. Experimental results on two si
arXiv:2604.14228v2 Announce Type: replace-cross Abstract: Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its architecture by analyzing the publicly available source code and comparing it with two independent open-source AI agent systems, OpenClaw and Hermes Agent, that answer many of similar or even the same design questions. Our analysis identifies five human values, philosophies, and needs that motivate the architecture: human decision authority, safety, security, and privacy, reliable execution, capability amplification, and contextual adaptability. We then trace them through thirteen design principles to implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline
arXiv:2604.09945v2 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes. While significant attention has been paid to such fairness concerns in the context of social biases, relatively little prior work has examined the presence of stereotypes in LVLMs related to cultural contexts such as religion, nationality, and socioeconomic status. In this work, we aim to narrow this gap by investigating how cultural contexts depicted in images influence the judgments LVLMs make about a person's moral, ethical, and political values. We conduct a multi-dimensional analysis of such value judgments in nine LVLMs using counterfactual image sets, which depict the same person across different cultural contexts. Our evaluation framework pairs descriptive analyses (Moral Foundations Theory categorization, lexical analyses, and valu
arXiv:2603.29466v2 Announce Type: replace-cross Abstract: Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or require access to training data that is typically unavailable. We derive a lightweight alternative through two approximations: a first-order Taylor expansion that expresses uncertainty in terms of the gradient of the prediction and the parameter covariance, and an isotropy assumption on the parameter covariance. Together, these yield epistemic uncertainty as the squared gradient norm and aleatoric uncertainty as the Bernoulli variance of the point prediction, from a single forward-backward pass through an unmodified pretrained model. We justify the isotropy assumption by showing that covariance estimates built from non-training data introduce structured distortions that isotropic covariance avoids, and that theoretical results on the spectral properties of large networks support the appro
arXiv:2603.02112v2 Announce Type: replace-cross Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as a minimal realization, where the model can recursively invoke itself to solve subtasks in isolated contexts. We prove that any computable problem admits a recursive decomposition of reasoning in which each subtask requires only exponentially smaller active context than standard autoregressive models; this strictly surpasses any context management approach confined to a single sequence, such as summarization. We further generalize our framework to modern agentic systems with arbitrary context processing and control flows, and prove that recursive models can achieve optimal power within this broader class. Experimentally, we test two settings: fine-tuning a pretrained base model for recursive SA
arXiv:2602.22897v3 Announce Type: replace-cross Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel omni-modal event graph approach, OmniGAIA synthesizes complex, multi-hop queries derived from real-world data that require cross-modal reasoning and external tool integration. Furthermore, we propose OmniAtlas, a native omni-modal foundation agent under tool-integrated reasoning paradigm with active omni-modal perception. Trained on trajec
arXiv:2602.20459v2 Announce Type: replace-cross Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow? We introduce PreScience, a dataset and benchmark for scientific forecasting built around 98K recent AI research papers, together with companion papers covering author publication histories and citation links, yielding 502K papers in total. The resulting paper records include titles, abstracts, disambiguated author identities, influential references, topic labels, citation trajectories, and metadata snapshotted to respect temporal cutoffs. We instantiate seven exemplar tasks: five paper-anchored tasks -- contribution generation, collaborator prediction, prior work selection, citation count prediction, and future combination prediction -- and two aggregate topic trend forecasting variants. We develop baselines ranging from simple heuristics and embedding methods to frontier language models and agentic systems, and introduce LACER, an L
arXiv:2602.07267v2 Announce Type: replace-cross Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on direct human task completion time annotations are costly, noisy, and difficult to scale across benchmarks. In this work, we propose BRIDGE, a unified psychometric framework that learns a latent difficulty scale from model responses and anchors it to human task completion time. Using a two-parameter logistic Item Response Theory model, we jointly estimate latent task difficulty and model capability from model performance data across multiple benchmarks. We demonstrate that latent task difficulty varies linearly with the logarithm of human completion time, allowing human task completion time to be inferred for new benchmarks from model performance alone. Leveraging this alignment, we forecast frontier model capabilities in terms of human task length and i
arXiv:2601.22710v2 Announce Type: replace-cross Abstract: Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a deployable API-only \cradd{exposure-reduction layer that reduces plaintext exposure} by translating text into an Alien Language via a vocabulary-scale bijection, enabling lossless recovery on the client side. Using only standard fine-tuning APIs, Alien Adaptation Training (AAT) adapts target models to operate directly on alienized inputs. Across four LLM backbones and seven benchmarks, AlienLM retains over 81\% of plaintext-oracle performance on average, substantially outperforming random-bijection and character-level baselines. Under adversaries with access to model weights, corpus statistics, and learning-based inverse translation, recovery attacks reconstruct fewer than 0.22\% of alienized toke
arXiv:2601.02813v3 Announce Type: replace-cross Abstract: Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised training, rather than targeted alignment. We introduce Human Aligning LLMs (HAL), a framework for aligning language models to conversational human-likeness using an interpretable, data-driven reward. HAL derives explicit conversational traits from contrastive dialogue data, combines them into a compact scalar score, and uses this score as a transparent reward signal for alignment with standard preference optimization methods. Using this approach, we align models of varying sizes without affecting their overall performance. In large-scale Chatbot Arena-style human evaluations, a model aligned with HAL is more frequently perceived as human-like in conversation. Because HAL operates
arXiv:2512.07843v2 Announce Type: replace-cross Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process. However, existing parallel reasoning approaches suffer from performance degradation compared to their sequential counterparts, and often rely on specialized inference engines. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that matches the accuracy of comparably sized sequential reasoning models while significantly reducing inference latency via three key innovations: 1) a two-stage parallel trajectory generator that produces high-quality parallel chain-of-thought data for supervised fine-tuning; 2) a trie-based rollout design that enables parallel reasoning on any off-the-shelf autoregressive inference engine; and 3) a parallelization-aware reinforcement learning frame
arXiv:2511.10687v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with process reward modeling to transform system evaluation to agent credit to response-level signals. Unlike prior approaches that rely only on attribution (Shapley) or step-level labels (PRM), our method produces local, signed, and credit-conserving signals. In success cases, Shapley-based credit assignment fairly allocates outcomes across agents and is refined into per-message rewards that promote cooperation while discouraging redundancy or sabotage; in failure cases, first-error localization yields repair-aware preferences that penalize harmful steps while rewarding corrective attempts. The resulting signals are bounded,
arXiv:2510.04391v5 Announce Type: replace-cross Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large language model (LLM) populations remains unknown. We applied psychological network analysis to vividness ratings from two validated questionnaires: the Vividness of Visual Imagery Questionnaire (VVIQ-2) and the Plymouth Sensory Imagery Questionnaire (PSIQ), across geographically and linguistically distinct human samples (Florida, Poland, and London; total N = 2,743) and six large language models (LLMs; Gemma3-12B/27B, their quantization-aware counterparts, Llama3.3-70B, and Llama4-16x17B). Imagination networks were constructed as regularized partial correlation graphs, with node centrality and community structure compared across populations using Pearson correlations and the Adjusted Rand Index (ARI). Human networks showed robust cross-population centrality correlations for expected in
arXiv:2508.16674v2 Announce Type: replace-cross Abstract: Medical report understanding from real-world document images is essential for generating patient-facing explanations and enabling structured information exchange in clinical systems. Existing VLMs and LLMs have shown strong performance on document understanding, but structured understanding of medical reports remains insufficiently benchmarked. Therefore, we introduce MedRepBench, a benchmark with 1,925 de-identified Chinese medical report images spanning diverse departments, patient demographics, and acquisition formats. In MedRepBench, we mainly focus on report-grounded interpretation rather than evaluating diagnostic reasoning, treatment recommendation, or the integration of patient history. The interpretation is defined as structured extraction of report fields (e.g., item, value, unit, reference range, abnormal flag) plus a patient-facing explanation grounded strictly in the report content. The benchmark primarily evaluates
arXiv:2607.00250v2 Announce Type: replace Abstract: Maltese, although a low-resource language, has its own text corpora and pretrained language models, but we are aware of only one real labelled PDF corpus for OCR training, 57 pages, far below what paragraph-level training needs. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract ensemble voted under a lexicon-anchored, ROVER-style scheme adapted for a low-resource setting. We call the Maltese submission LV-ROVER-MLT: an engineered adaptation of LV-ROVER's voting algorithm, not a new one, submitted to the DocEng 2026 competition. All results below are dev-set figures from the competition's own benchmark; the held-out real test CER is unknown at the time of writing and this paper does not claim one. We report results on a 422-paragraph benchmark against a fine-tuned Tesseract baseline with a character error rate of 0.0234. Ensemble recognition alone, scored under the same label conv
arXiv:2606.15510v2 Announce Type: replace Abstract: AthDGC ("Athens-PROIEL") is an open, end-to-end workflow and dataset. It is, to the best of our knowledge, the first openly licensed dependency-parsed treebank of Greek that spans eight diachronic periods, namely Archaic, Classical, Koine, Late Antique, Byzantine, Late Byzantine, Early Modern, and Modern Greek, under a single PROIEL XML 2.0 schema, with verse-level cross-alignment of the New Testament to Latin (Vulgate), Gothic (Wulfila), Old Church Slavonic (Marianus), and Classical Armenian. AthDGC builds on the PROIEL Treebank Family (Haug and Johndal 2008; Eckhoff et al. 2018), which established the schema and the Koine-Greek reference set for the project. Annotation uses the Stanford Stanza PROIEL-trained workflow; sentence-level alignment uses LaBSE, a multilingual sentence-embedding model; word-level alignment uses multilingual-BERT attention through the AwesomeAlign procedure. The v0.4 release provides curated samples and the
arXiv:2606.12569v2 Announce Type: replace Abstract: We present eCream-MedCorpus, a new and unique large-scale dataset of clinical notes produced in Emergency Departments of Italian hospitals. The corpus, in its current version, is composed of approximately 4 million clinical notes fully anonymized, covering diverse phases of patient care during the stay in the emergency department. In addition, a subset of about six thousand notes has been manually annotated by clinical experts through a structured Case Report Form (CRF) containing 132 items relevant for two patient situations in emergency departments, dyspnea and loss of consciousness. Items may assume numerical values (e.g., for blood saturation), categorical (e.g., for level of consciousness ), binary (e.g., for presence of traumas), and mixed value types. The annotation process involved multiple clinicians and underwent iterative revision to resolve ambiguities in item formulation, resulting in a richly structured (although high im