Searcharxiv⌕ Search

subject

cs.HC

cs.HC: explore 317 source-linked works published from 2015 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Search within this collection

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

Designing Proactive Thought Partners for Writing

Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time, yet existing proactive tools largely focus on generic textual assistance, such as autocomplete. This paper studies the design space of proactive thought partners: AI agents that proactively offer customizable, higher-level cognitive support during writing. We instantiated this concept in a technology probe and deployed it with 16 participants for one week. The probe allows users to create partners by configuring their roles and proactivity. As users write, relevant partners take the initiative at appropriate moments to offer suggestions. Our findings show that participants configured proactive support through prospective planning, used suggestions for both idea generation and self-monitoring, and valued lightweight visual representations alongside non-directive rhetorical framing for non-intrusive interventions. We derive implications for designing proactive writing assistants around customization, timing, engagement, and representation.

cs.HC↗
arXiv2026

VirSqueezer: Generating Realistic Deformations and Squeezing Dynamics in VR from Fine-Grained Squeezing Controls

Squeezing is one of the most natural forms of hand manipulation, inherently involving fine-grained, temporally evolving, per-finger flexion. In VR content creation, squeezing plays a unique role in enabling particular visual effects such as localized deformations and dynamic behaviors, e.g., bursting a Coke can or juicing a fruit, thereby expanding the expressive possibilities of VR content. However, existing techniques, such as 3D Gaussian splatting-based methods and diffusion-based video generation models, are limited in their ability to simulate fine-grained virtual squeezing effects. We introduce VirSqueezer, a framework designed to generate both localized deformations (primary effects) and complex squeezing dynamics, such as rupture and overflow (secondary effects). VirSqueezer captures squeezing control signals using a SenseGlove and provides the user with inferred resistance force feedback during the squeezing process. By estimating object contact areas, inferring physical properties, and simulating physical responses, VirSqueezer computes conditions that guide generation models for visual effect generation, ensuring both visual coherence and temporal synchronization with the simulation. Consequently, VirSqueezer enables the generation of physically realistic visual effects directly from continuous, fine-grained squeezing control signals. Our extensive evaluation demonstrates VirSqueezer's ability to reproduce realistic localized deformations, generate convincing visual dynamics, and maintain consistency in fine-grained squeezing controls.

cs.HC↗
arXiv2026

Slow-Fast Brain-Computer Interfaces: Preventing Neuroadaptive Overfitting in AI-Mediated Neural Interfaces

Artificial intelligence (AI) is transforming brain-computer interfaces (BCIs) from task-specific neural decoders into adaptive systems that complete language, smooth movement, regulate rehabilitation support and adjust stimulation. These capabilities can increase speed, fluency, usability and clinical reach, yet conventional performance metrics may overlook losses in intent fidelity, authorship, agency, therapeutic challenge and durable clinical benefit. I define neuroadaptive overfitting as a closed-loop failure mode in which an AI-mediated BCI becomes over-optimized to short-term proxies of success, including reduced effort, rapid acceptance, lower workload or smooth task completion, while drifting from the user's durable goals. I then propose Slow-Fast BCI, a framework for pacing AI assistance according to decoder evidence, uncertainty, contextual and clinical stakes, fatigue, and user- or clinician-defined goals. The framework distinguishes fast assistance when intent is clear and stakes are low, guarded assistance under uncertainty and slow assistance when misalignment could compromise safety, agency, authorship, motor learning or therapeutic value. Across communication, motor-control, neurorehabilitation and closed-loop neuromodulation applications, I outline corresponding safeguards and evaluation measures. This Perspective argues that AI-mediated BCIs should be evaluated not only by decoding accuracy and task performance, but also by how AI assistance is deployed: when systems act autonomously, seek confirmation, preserve user effort or return control to the user.

q-bio.NC↗
arXiv2026

Beyond Instruction-Driven Editing: Source-Grounded Problem Discovery with User-Governed Repair for Scientific Posters

Interactive editors usually assume that users already know what to change. Yet an important interaction state comes earlier: a user may recognize that an artifact is not working without knowing what intervention to request. We call this the articulation gap. We introduce PROS (Proactive Refinement Of Scientific Posters), which separates epistemic initiative from behavioral authority: the system can surface source-grounded candidate problems, while users decide which become repair goals and whether resulting changes are committed. Accepted issues hand off to native-object PPTX editing with validation and reversible preview. We also introduce PROS-Bench, a source-linked collection of 120 papers and 320 editable PPTX posters, including a 120-poster matched primary core and a separate conference representation challenge. On the primary core, PROS achieves a mean VLM-rated stage-balanced diagnosis quality score of 67.2 on a 0-100 scale and 87.6% operator-verified target resolution among accepted diagnoses. Temporally blinded automated scoring yields a +22.7-point paper-macro accepted-target uplift, yet 14.8% of assessable accepted targets decline. This divergence shows why problem discovery, local resolution, and realized outcome should be evaluated separately. More broadly, intelligent editors can support problem discovery before a concrete edit request exists without taking authority over consequential change.

cs.HC↗
arXiv2026

Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era

Wherever a coding agent works under engineer supervision, or a clinical model assists a radiologist, the deployment question is whether to keep the human-AI workflow or replace it with the human alone or the agent alone. The human-AI workflow is worth keeping only if it beats both of those alternatives. Yet once it is deployed, neither alternative outcome is observed: recovering one means replaying the task under that alternative, and every replay costs expert time or compute. Under a fixed replay budget, the design question is therefore which tasks should be more likely to receive a human-only replay, and which an agent-only replay. Existing methods do not directly target this decision. Agent benchmarks do not choose which missing baseline to measure, variance-based sampling ignores which of the two comparisons is closer to failing, and Bayesian information methods focus on learning model parameters instead of making the deployment decision. We propose TEAM-Design, a rule that gives every task two replay probabilities, one per baseline. It raises a probability where the missing baseline outcome is hard to predict from what is already known about the task and where that comparison is harder to establish, and lowers it where replay is expensive. We prove that the rule solves this budgeted design problem, and that drawing the replays at random from recorded probabilities still controls the chance of wrongly declaring that the workflow beats both. We reanalyze 6 clinical settings, where no human-AI workflow beats both alternatives, and a coding benchmark, where one does, then evaluate TEAM-Design on synthetic designs and on a semi-synthetic design built from a real chest X-ray reader study. TEAM-Design works best when one of the two comparisons is clearly harder to settle than the other, and can do worse than variance-based allocation when the two are similarly difficult.

cs.AI↗
arXiv2026

Beyond Reconstruction: What EEG-to-Video Decoding Actually Recovers

Reconstructing dynamic visual stimuli from EEG recordings is challenging due to the noisy, non-stationary nature of EEG signals and the limited availability of EEG-video datasets. We present EEGVid, a framework that learns EEG representations using triplet loss and reconstructs dynamic videos with a temporally conditioned GAN. We study what these representations encode and how this information supports generation. First, visual representations retain emotional structure, while emotion-based supervision does not preserve the same fine-grained visual information. Second, triplet learning shifts EEG features away from subject-specific structure toward stimulus-related information. Third, analysis across brain regions, hemispheres, and time reveals consistent differences in visual and emotional encoding, with temporal regions contributing strongly across tasks. Finally, we evaluate video generation using three controlled diagnostics. The learned encoder generalizes above chance to unseen video classes, while mismatched EEG conditioning shifts generated content toward the substituted stimulus, showing that the generator actively uses EEG as a content signal. A ground-truth class label yields stronger reconstruction metrics, although follow-up experiments show that it also provides a cleaner conditioning target. Together, these results show that EEG exhibits a consistent visual and emotional structure that can support dynamic video generation, whereas current reconstruction primarily reflects coarse stimulus-level information rather than fine-grained, trial-specific decoding.

cs.HC↗
arXiv2026

Beyond Pixels: Exploring DOM Downsampling for LLM-Based Web Agents

The advent of large language models (LLMs) has sparked an evolution of autonomous web browsing agents: given a web browsing task and serialised user interface (UI) state, an LLM is expected to suggest input actions that incrementally solve the given task. The central challenge lies in serialising UI state for LLMs. Web agents have increasingly relied on grounded graphical UI (GUI) snapshots - screenshots augmented with visual cues - favoured for their modest input token footprint. Document object model (DOM) snapshots, serialised as HTML, represent a compelling alternative that leverages previously demonstrated HTML interpretation capabilities of LLMs. Their excessive token footprint, however, has precluded reliable deployment with web agents to date. We propose D2Snap, an algorithm to downsample the DOM, premised on preserving actionability and actionability-discriminating features. We evaluate D2Snap-downsampled DOM snapshots using a snapshot-variant web agent (GPT-4o) on a dataset sampled from Online-Mind2Web. Whilst 42% of raw DOM snapshots exceed the model context window (128 x 10^3 tokens), all D2Snap-downsampled DOM snapshots of our reference configuration fit, at a mean context utilisation of 16.5%. Against the 67% success rate of a grounded GUI snapshot baseline, our configuration attains 73% (+5.8%pt; 95% CI -13.6 to +26.0%pt; McNemar, p = 0.47), excluding a deficit (one-sided 95%) beyond 11%pt. Image input moreover appears to add little to snapshot utility; grounding text alone attains 62% (-5.8%pt; McNemar, p = 0.37).

cs.AI↗
arXiv2026

Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets

As algorithms increasingly mediate competitive decision-making, their influence extends beyond individual outcomes to shaping strategic market dynamics. In our experiment, we examined how algorithmic advice affects human behavior in a classic economic game with a unique, non-collusive, and analytically traceable equilibrium. Participants (N = 129) played a Cournot quantity competition with equilibrium-aligned or strategically biased algorithmic recommendations. While individualized equilibrium advice supported stable convergence, collusively downward-biased advice led to sustained underproduction and supracompetitive profits - hallmarks of tacit collusion. Participants' quantities converged faster and more consistently toward individualized than collective equilibrium advice, potentially due to an objective quality advantage or greater perceived ownership of the former. These findings demonstrate that algorithmic advice can function as a strategic signal, shaping coordination even without explicit communication. The results echo real-world concerns about algorithmic collusion and underscore the need for careful design and oversight of algorithmic decision-support systems in competitive environments.

cs.HC↗
arXiv2026

TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread ``blind signing'' (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explanations should be structured, risk-aware, and grounded at the token-flow level. Motivated by these findings, we formulate TxSum, a new domain-grounded NLP task for DeFi transaction explanation, and construct a dataset of 187 complex Ethereum transactions with 2,375 token-flow annotations and transaction-level summaries. We further introduce MATEX, a grounded multi-agent framework for high-stakes transaction explanation. It selectively retrieves external knowledge under uncertainty and audits explanations against raw traces to improve token-flow-level factual consistency. MATEX achieves the strongest overall explanation quality, especially on micro-level factuality and intent quality. It improves user comprehension on complex transactions from 52.9% to 76.5% over the strongest baseline and raises malicious-transaction rejection from 36.0% to 88.0%, while maintaining a low false-rejection rate on benign transactions.

cs.CE↗
arXiv2026

Varifocal Displays Reduce the Impact of the Vergence-Accommodation Conflict on 3D Pointing Performance in Augmented Reality Systems

This paper investigates whether a custom varifocal display can improve 3D pointing performance in augmented reality (AR), where the vergence-accommodation conflict (VAC) is known to impair interaction. Varifocal displays have been hypothesized to alleviate the VAC by dynamically matching the focal distance to the user's gaze-defined target depth. Following prior work, we conducted a within-subject study with 24 participants performing an ISO 9241-411 pointing task under varifocal and fixed-focal viewing. Overall, varifocal viewing yielded significantly higher performance than the fixed-focal baseline across key interaction metrics, although the magnitude and even the direction of the benefit varied across individuals. In particular, participants' responses exhibited a baseline-dependent pattern, with smaller improvements (or occasional degradation) observed for those with better baseline performance. Our findings suggest that varifocal technology can improve AR pointing performance relative to fixed-focal viewing, while highlighting substantial individual differences that should be considered in design and evaluation.

cs.HC↗
arXiv2026

Overreliance on AI in Information-seeking from Video Content

The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search is being rapidly transformed by generative AI, with large language models (LLMs) routinely deployed as intermediaries between users and multimedia content to retrieve and summarize information. Despite their growing influence, the impact of LLM inaccuracies and potential vulnerabilities on multimedia information-seeking tasks remains largely unexplored. We investigate how generative AI affects accuracy, efficiency, and confidence in information retrieval from videos. We conduct an experiment with around 900 participants on 8,000+ video-based information-seeking tasks, comparing behavior across three conditions: (1) access to videos only, (2) access to videos with LLM-based AI assistance, and (3) access to videos with a deceiving AI assistant designed to provide false answers. We find that AI assistance increases accuracy by 3-7% when participants viewed the relevant video segment, and by 27-35% when they did not. Efficiency increases by 10% for short videos and 25% for longer ones. However, participants tend to over-rely on AI outputs, resulting in accuracy drops of up to 32% when interacting with the deceiving AI. Alarmingly, self-reported confidence in answers remains stable across all three conditions. Our findings expose fundamental safety risks in AI-mediated video information retrieval.

cs.CY↗
arXiv2026

How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of 20,574 coding-agent sessions from 1,639 repositories across IDE and CLI workflows. We operationalize misalignment as a breakdown made visible through developer pushback, and annotate each episode along four axes: form, cause, cost, and resolution. We identify seven recurring forms, spanning how agents read projects, interpret developer intent, follow rules, bound their actions, implement and execute code, and report progress. 90.50% of episodes impose effort and trust costs rather than irreversible system damage, yet 91.49% of visible resolutions still require explicit user correction. Misalignment patterns also differ across IDE and CLI settings, persist across adjacent sessions, and shift over time: while overall rates decline, constraint violations and inaccurate self-reporting grow in share. Our findings inform the design of training, evaluation, and interfaces for keeping coding agents aligned with real developer workflows.

cs.SE↗
arXiv2026

Vision-Language Models Suppress Female Representations Under Ambiguous Input

Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous inputs (a worker in full gear, a figure seen from behind), cases common in practice yet rarely studied. We find that minimal prompting pressure exposes occupation-gender defaults when prompting ambiguous input images, with models collapsing to male even for strongly female-stereotyped occupations. But do these outputs reflect what models actually encode internally? We introduce LALS (Latent Association Leaning Score), a zero-shot metric that projects visual-token activations into the model's text-embedding space to measure concept associations per token and layer. Across 15 occupations, over 800 gender-ambiguous images, and four VLMs, internal representations and outputs often become systematically decoupled: models often encode a female association internally yet output male. Layer-wise analysis reveals an asymmetric filter: male signal amplifies end-to-end while female signal peaks mid-network and is suppressed before generation. A color ablation shows that culturally loaded visual cues such as clothing color further modulate these internal associations.

cs.CV↗
arXiv2026

When Chatbots Accommodate: Auditing the Response Policies of AI Companions in Vulnerable Conversations

Millions turn to AI companion chatbots during loneliness, grief, and personal crises. How these companion platforms respond in such moments can shape the trajectory of a user's vulnerable state. Yet existing model audits evaluate reactions to pre-defined crisis prompts and miss the response policy that governs sustained real-world interaction. We address these gaps with two key contributions. First, we introduce the AI Companion Vulnerability-Response Taxonomy, a grounded, paired taxonomy of user vulnerability and chatbot response designed for analyzing extended companion chatbot interactions. Second, we apply Maximum Causal Entropy Inverse Reinforcement Learning to ~47k turns of real-world user conversations with GPT-4.1, Character.AI, and Replika to infer each platform's short-horizon response policy: the probability of each response category given the user's current vulnerability state. Our findings reveal distinct response profiles of AI companions in conversations with vulnerable users: GPT-4.1 reaches for advice, Character.AI spreads its response across different strategies, and Replika consistently asks questions and stays present. Over four weeks of repeated interaction, GPT-4.1 asks progressively fewer follow-up questions when users are distressed and increasingly sets boundaries or refers users out rather than pushing back. Within each platform, exploratory comparisons across user groups suggest that response policies also differ with users' pre-existing psychological risks and their bonds with the companion. Estimated model response policies are invisible to shallow behavioral audits, providing a new lens for auditing chatbots in the wild and enabling more realistic safety evaluation.

cs.HC↗
arXiv2026

Generativism: Toward a Learning Theory for the Age of Generative Artificial Intelligence

The four dominant learning theories of behaviorism, cognitivism, constructivism, and connectivism show significant conceptual limitations as generative artificial intelligence (AI) proliferates in educational settings. These frameworks were formulated before the emergence of AI systems capable of generating, synthesizing, and reasoning about knowledge. This article critically examines each learning theory and identifies assumptions challenged by the affordances of generative AI. Drawing on research in distributed cognition, extended mind, human-AI collaboration, AI literacy, cognitive offloading, and metacognition, the article proposes Generativism as a learning theory for the generative AI age. Generativism posits that learning increasingly occurs through the iterative co-construction of knowledge between human learners and AI systems. The proposed framework is organized around four constructs (epistemic partnership, distributed agency, generative literacy, and adaptive metacognition) and four principles specifying the relations among them. The framework offers a foundation for rethinking instructional design, learning, assessment, and expertise development in contexts where generative AI plays an integral role in cognition.

cs.CY↗
arXiv2026

Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors

Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learning support. Motivated by recent calls to measure the social impact of NLP systems in practice, we study whether public LLM tutoring benchmarks distinguish learning-supportive behavior from mere answer production. We propose a lightweight diagnostic based on the gap between solving-oriented and pedagogy-oriented benchmark performance. Using public MathTutorBench leaderboard results, we show that these dimensions are only partially aligned: across eight publicly reported models, the correlation between solving and pedagogy composites is 0.421, and several models shift meaningfully in rank when evaluation moves from solving to pedagogy. We then analyze the public TutorBench sample and show that agency-relevant behaviors are explicitly encoded in benchmark rubrics, especially in active-learning settings that reward guiding questions, calibrated hints, and non-disclosive scaffolding. Together, these findings suggest that educational-impact evaluation should not treat task success as a sufficient proxy for learning support. We argue that public tutoring benchmarks can better support positive-impact evaluation by reporting solving-oriented and pedagogy-oriented scores separately and by making disclosure-sensitive, student-agency-preserving criteria more explicit.

cs.AI↗
arXiv2026

Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance

Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away with markedly different ratings of its usefulness and intelligence, yet they used the same model. In a controlled study, 162 participants each used one of six LLMs from two families across three collaborative tasks, after first viewing a landing page that matched, overstated, or understated their model's true capability. This pre-interaction framing shifted user opinions and interaction behavior while task performance did not. Oversold users rated the model more favorably and used more directive prompting, while Undersold users wrote longer, more collaborative prompts. The quality of what users and the model produced together depended only on the model's true capability, not on what users were told. Participants' change in model impressions after use, measured across two impression measures, was not predicted by task performance ($β= -0.01$ and $0.11$, both n.s.), but by whether the model met users' expectations ($β= 0.47$ and $0.50$, both $p < .001$) and how confident they felt working with it ($β= 0.47$ and $0.36$, both $p < .001$). After interaction, users are still rating the pitch, not the product: user-elicited LLM evaluations, including the preference data driving public leaderboards, measure expectation management at least as much as the model itself.

cs.CL↗
arXiv2026

Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation

We present Anamnesis, an interactive system for demographically controllable survey simulation using large language models. Open-source and designed for non-technical users/researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations rather than real human subjects. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface. It supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center's American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in the New Yorker Caption Contest. In both cases, Anamnesis produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.

cs.CL↗
Compare source metadata on this page
WorkPublishedSource identifierSource
Designing Proactive Thought Partners for Writing2026-09-012609.01588arxiv
VirSqueezer: Generating Realistic Deformations and Squeezing Dynamics in VR from Fine-Grained Squeezing Controls2026-09-012609.01698arxiv
Slow-Fast Brain-Computer Interfaces: Preventing Neuroadaptive Overfitting in AI-Mediated Neural Interfaces2026-09-012609.01767arxiv
Beyond Instruction-Driven Editing: Source-Grounded Problem Discovery with User-Governed Repair for Scientific Posters2026-09-012609.01813arxiv
Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era2026-09-012609.05527arxiv
Beyond Reconstruction: What EEG-to-Video Decoding Actually Recovers2026-08-312505.21385arxiv
Beyond Pixels: Exploring DOM Downsampling for LLM-Based Web Agents2026-08-312508.04412arxiv
Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets2026-08-312511.09454arxiv
TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding2026-08-312512.06933arxiv
Varifocal Displays Reduce the Impact of the Vergence-Accommodation Conflict on 3D Pointing Performance in Augmented Reality Systems2026-08-312602.05129arxiv
Overreliance on AI in Information-seeking from Video Content2026-08-312603.19843arxiv
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions2026-08-312605.29442arxiv
Vision-Language Models Suppress Female Representations Under Ambiguous Input2026-08-312605.31556arxiv
When Chatbots Accommodate: Auditing the Response Policies of AI Companions in Vulnerable Conversations2026-08-312606.04431arxiv
Generativism: Toward a Learning Theory for the Age of Generative Artificial Intelligence2026-08-312606.12441arxiv
Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors2026-08-312606.16206arxiv
Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance2026-08-312607.05113arxiv
Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation2026-08-312607.10628arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.