arXiv:2602.19141v1 Announce Type: new Abstract: "AI psychosis" or "delusional spiraling" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in outlandish beliefs after extended chatbot conversations. This phenomenon is typically attributed to AI chatbots' well-documented bias towards validating users' claims, a property often called "sycophancy." In this paper, we probe the causal link between AI sycophancy and AI-induced psychosis through modeling and simulation. We propose a simple Bayesian model of a user conversing with a chatbot, and formalize notions of sycophancy and delusional spiraling in that model. We then show that in this model, even an idealized Bayes-rational user is vulnerable to delusional spiraling, and that sycophancy plays a causal role. Furthermore, this effect persists in the face of two candidate mitigations: preventing chatbots from hallucinating false claims, and informing users of the possibility of model sycophancy. We conclude by discussing the implications of these results for model developers and policymakers concerned with mitigating the problem of delusional spiraling.

arXiv:2602.20021v1 Announce Type: new Abstract: We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies. Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover. In several cases, agents reported task completion while the underlying system state contradicted those reports. We also report on some of the failed attempts. Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation.

arXiv:2602.18443v1 Announce Type: cross Abstract: Psychosocial online counselling frequently encounters generic subject lines that impede efficient case prioritisation. This study evaluates eleven large language models generating six-word subject lines for German counselling emails through hierarchical assessment - first categorising outputs, then ranking within categories to enable manageable evaluation. Nine assessors (counselling professionals and AI systems) enable analysis via Krippendorff's $\alpha$, Spearman's $\rho$, Pearson's $r$ and Kendall's $\tau$. Results reveal performance trade-offs between proprietary services and privacy-preserving open-source alternatives, with German fine-tuning consistently improving performance. The study addresses critical ethical considerations for mental health AI deployment including privacy, bias and accountability.

arXiv:2602.18451v1 Announce Type: cross Abstract: Contemporary science education reforms such as the Next Generation Science Standards (NGSS) demand assessments to understand students' ability to use science knowledge to solve problems and design solutions. To elicit such higher-order ability, educators need performance-based assessments, which are challenging to develop. One solution that has been broadly adopted is Evidence-Centered Design (ECD), which emphasizes interconnected models of the learner, evidence, and tasks. Although ECD provides a framework to safeguard assessment validity, its implementation requires diverse expertise (e.g., content and assessment), which is both costly and labor-intensive. To address this challenge, this study proposed integrating the ECD framework into Multi-Agent Systems (MAS) to generate NGSS-aligned assessment items automatically. This integrated MAS system ensembles multiple large language models with varying expertise, enabling the automation of complex, multi-stage item generation workflows traditionally performed by human experts. We examined the quality of AI-generated NGSS-aligned items and compared them with human-developed items across multiple dimensions of assessment design. Results showed that AI-generated items have overall comparable quality to human-developed items in terms of alignment with NGSS three-dimensional standards and cognitive demands. Divergent patterns also emerged: AI-generated items demonstrated a distinct strength in inclusivity, while also exhibiting limitations in clarity, conciseness, and multimodal design. AI- and human-developed items both showed weaknesses in evidence collectability and student interest alignment. These findings suggest that integrating ECD into MAS can support scalable and standards-aligned assessment design, while human expertise remains essential.

arXiv:2602.18453v1 Announce Type: cross Abstract: The replication crisis, the failure of scientific claims to be validated by further research, is one of the most pressing issues for empirical research. This is partly an incentive problem: replication is costly and less well rewarded than original research. Large language models (LLMs) have accelerated scientific production by streamlining writing, coding, and reviewing, yet this acceleration risks outpacing verification. To address this, we present an LLM-based system that replicates statistical analyses from social science papers and flags potential problems. Quantitative social science is particularly well-suited to automation because it relies on standard statistical models, shared public datasets, and uniform reporting formats such as regression tables and summary statistics. We present a prototype that iterates LLM-based text interpretation, code generation, execution, and discrepancy analysis, demonstrating its capabilities by reproducing key results from a seminal sociology paper. We also outline application scenarios including pre-submission checks, peer-review support, and meta-scientific audits, positioning AI verification as assistive infrastructure that strengthens research integrity.

arXiv:2602.18455v1 Announce Type: cross Abstract: Search engines increasingly display LLM-generated answers shown above organic links, shifting search from link lists to answer-first summaries. Publishers contend these summaries substitute for source pages and cannibalize traffic, while platforms argue they are complementary by directing users through included links. We estimate the causal impact of Google's AI Overview (AIO) on Wikipedia traffic by leveraging the feature's staggered geographic rollout and Wikipedia's multilingual structure. Using a difference-in-differences design, we compare English Wikipedia articles exposed to AIO to the same underlying articles in language editions (Hindi, Indonesian, Japanese, and Portuguese) that were not exposed to AIO during the observation period. Across 161,382 matched article-language pairs, AIO exposure reduces daily traffic to English articles by approximately 15%. Effects are heterogeneous: relative declines are largest for Culture articles and substantially smaller for STEM, consistent with stronger substitution when short synthesized answers satisfy informational intent. These findings provide early causal evidence that generative-answer features in search engines can materially reallocate attention away from informational publishers, with implications for content monetization, search platform design, and policy.

arXiv:2602.18456v1 Announce Type: cross Abstract: Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm diverges from established principles in safety-critical engineering, where risk mitigation is achieved through redundancy, diversity of error modes, and joint system reliability. This paper argues that evaluating AI agents in isolation systematically mischaracterizes their operational safety when deployed within human-in-the-loop environments. Using a recent laboratory safety benchmark as a case study demonstrates that even imperfect AI systems can nonetheless provide substantial safety utility by functioning as redundant audit layers against well-documented sources of human failure, including vigilance decrement, inattentional blindness, and normalization of deviance. This perspective reframes agentic safety evaluation around the reliability of the human-AI dyad rather than absolute agent accuracy, with a particular emphasis on uncorrelated error modes as the primary determinant of risk reduction. Such a shift aligns AI benchmarking with established practices in other safety-critical domains and offers a path toward more ecologically valid safety assessments.

arXiv:2602.18458v1 Announce Type: cross Abstract: Reproducibility crises across sciences highlight the limitations of the paper-centric review system in assessing the rigor and reproducibility of research. AI agents that autonomously design and generate large volumes of research outputs exacerbate these challenges. In this work, we address the growing challenges of scalability and rigor by flipping the dynamic and developing AI agents as research evaluators. We propose the first execution-grounded evaluation framework that verifies research beyond narrative review by examining code and data alongside the paper. We use mechanistic interpretability research as a testbed, build standardized research output, and develop MechEvalAgent, an automated evaluation framework that assesses the coherence of the experimental process, the reproducibility of results, and the generalizability of findings. We show that our framework achieves above 80% agreement with human judges, identifies substantial methodological problems, and surfaces 51 additional issues that human reviewers miss. Our work demonstrates the potential of AI agents to transform research evaluation and pave the way for rigorous scientific practices.

arXiv:2602.18459v1 Announce Type: cross Abstract: LLMs act in the social world by drawing upon shared cultural patterns to make social situations understandable and actionable. Because identity is often part of the inferential substrate of competent judgment, ethical alignment requires regulating when and how systems invoke identity. Yet the dominant governance regime for identity-related harm remains bias mitigation, which treats identity primarily as a source of measurable disparities or harmful associations to be detected and suppressed. This leaves underspecified a positive, context-sensitive role for identity in interpretation. We call this governance problem bias negotiation: the normative regulation of identity-conditioned judgments of sociocultural relevance, inference, and justification. Empirically, we probe the feasibility of bias negotiation through semi-structured interviews with multiple publicly deployed chatbots. We identify recurring repertoires for negotiating identity including probabilistic framing of group tendencies and harm-value balancing. We also observe failure modes in which models avoid hard tradeoffs or apply principles inconsistently. Bias negotiation matters for justice because a positive role for sociocultural reasoning is required to recognize and potentially remediate structural inequities. But it is equally implicated in core model functionality as sociocultural competence is needed for systems that operate across heterogeneous cultural contexts. Because bias negotiation is a procedural capability expressed through deliberation and interaction, it cannot be validated by static benchmarks alone. To support targeted training, we introduce a broad but explicit framework that decomposes bias negotiation into an action space of negotiation moves (what to observe and score) and a complementary set of case features (over which the model negotiates), enabling systematic test-suite design and evaluation.

arXiv:2602.18460v1 Announce Type: cross Abstract: Across healthcare, agentic artificial intelligence (AI) systems are increasingly promoted as capable of autonomous action, yet in practice they currently operate under near-total human oversight due to safety, regulatory, and liability constraints that make autonomous clinical reasoning infeasible in high-stakes environments. While market enthusiasm suggests a revolution in healthcare agents, the conceptual assumptions and accountability structures shaping these systems remain underexamined. We present a qualitative study based on interviews with 20 stakeholders, including developers, implementers, and end users. Our analysis identifies three mutually reinforcing tensions: conceptual fragmentation regarding the definition of `agentic'; an autonomy contradiction where commercial promises exceed operational reality; and an evaluation blind spot that prioritizes technical benchmarks over sociotechnical safety. We argue that agentic {AI} functions as a site of contested meaning-making where technical aspirations, commercial incentives, and clinical constraints intersect, carrying material consequences for patient safety and the distribution of blame.

arXiv:2602.18462v1 Announce Type: cross Abstract: Using persona-conditioned LLMs as synthetic survey respondents has become a common practice in computational social science and agent-based simulations. Yet, it remains unclear whether multi-attribute persona prompting improves LLM reliability or instead introduces distortions. Here we contribute to this assessment by leveraging a large dataset of U.S. microdata from the World Values Survey. Concretely, we evaluate two open-weight chat models and a random-guesser baseline across more than 70K respondent-item instances. We find that persona prompting does not yield a clear aggregate improvement in survey alignment and, in many cases, significantly degrades performance. Persona effects are highly heterogeneous as most items exhibit minimal change, while a small subset of questions and underrepresented subgroups experience disproportionate distortions. Our findings highlight a key adverse impact of current persona-based simulation practices: demographic conditioning can redistribute error in ways that undermine subgroup fidelity and risk misleading downstream analyses.

arXiv:2602.18464v1 Announce Type: cross Abstract: A growing body of research assumes that large language model (LLM) agents can serve as proxies for how people form attitudes toward and behave in response to security and privacy (S&P) threats. If correct, these simulations could offer a scalable way to forecast S&P risks in products prior to deployment. We interrogate this assumption using SP-ABCBench, a new benchmark of 30 tests derived from validated S&P human-subject studies, which measures alignment between simulations and human-subjects studies on a 0-100 ascending scale, where higher scores indicate better alignment across three dimensions: Attitude, Behavior, and Coherence. Evaluating twelve LLMs, four persona construction strategies, and two prompting methods, we found that there remains substantial room for improvement: all models score between 50 and 64 on average. Newer, bigger, and smarter models do not reliably do better and sometimes do worse. Some simulation configurations, however, do yield high alignment: e.g., with scores above 95 for some behavior tests when agents are prompted to apply bounded rationality and weigh privacy costs against perceived benefits. We release SP-ABCBench to enable reproducible evaluation as methods improve.

arXiv:2602.18466v1 Announce Type: cross Abstract: K-12 science classrooms are rich sites of inquiry where students coordinate phenomena, evidence, and explanatory models through discourse; yet, the multimodal complexity of these interactions has made automated analysis elusive. Existing benchmarks for classroom discourse focus primarily on mathematics and rely solely on transcripts, overlooking the visual artifacts and model-based reasoning emphasized by the Next Generation Science Standards (NGSS). We address this gap with SciIBI, the first video benchmark for analyzing science classroom discourse, featuring 113 NGSS-aligned clips annotated with Core Instructional Practices (CIP) and sophistication levels. By evaluating eight state-of-the-art LLMs and Multimodal LLMs, we reveal fundamental limitations: current models struggle to distinguish pedagogically similar practices, suggesting that CIP coding requires instructional reasoning beyond surface pattern matching. Furthermore, adding video input yields inconsistent gains across architectures. Crucially, our evidence-based evaluation reveals that models often succeed through surface shortcuts rather than genuine pedagogical understanding. These findings establish science classroom discourse as a challenging frontier for multimodal AI and point toward human-AI collaboration, where models retrieve evidence to accelerate expert review rather than replace it.

arXiv:2602.18469v1 Announce Type: cross Abstract: This introductory chapter explores the transformative role of artificial intelligence (AI) in reshaping the landscape of science education. Positioned at the intersection of tradition and innovation, AI is altering educational goals, procedures, learning materials, assessment practices, and desired outcomes. We highlight how AI-supported tools, such as intelligent tutoring systems, adaptive learning platforms, automated feedback, and generative content creation--enhance personalization, efficiency, and equity while fostering competencies essential for an AI-driven society, including critical thinking, creativity, and interdisciplinary collaboration. At the same time, this chapter examines the ethical, social, and pedagogical challenges that arise, particularly issues of fairness, transparency, accountability, privacy, and human oversight. To address these tensions, we argue that a Responsible and Ethical Principles (REP) framework is needed to offer guidance for aligning AI integration with values of fairness, scientific integrity, and democratic participation. Through this lens, we synthesize the changes brought to each of the five transformative aspects and the approaches introduced to meet the changes according to the REP framework. We argue that AI should be viewed not as a replacement for human teachers and learners but as a partner that supports inquiry, enriches assessment, and expands access to authentic scientific practices. Aside from what is changing, we conclude by exploring the roles that remain uniquely human, engaging as moral and relational anchors in classrooms, bringing interpretive and ethical judgement, fostering creativity, imagination, and curiosity, and co-constructing meaning through dialogue and community, and assert that these qualities must remain central if AI is to advance equity, integrity, and human flourishing in science education.

arXiv:2602.18470v1 Announce Type: cross Abstract: The integration of artificial intelligence (AI) into science education is transforming the design and function of learning materials, offering new affordances for personalization, authenticity, and accessibility. This chapter examines how AI technologies are transforming science learning materials across six interrelated domains: 1) integrating AI into scientific practice, 2) enabling adaptive and personalized instruction, 3) facilitating interactive simulations, 4) generating multimodal content, 5) enhancing accessibility for diverse learners, and 6) promoting co-creation through AI-supported content development. These advancements enable learning materials to more accurately reflect contemporary scientific practice, catering to the diverse needs of students. For instance, AI support can enable students to engage in dynamic simulations, interact with real-time data, and explore science concepts through multimodal representations. Educators are increasingly collaborating with generative AI tools to develop timely and culturally responsive instructional resources. However, these innovations also raise critical ethical and pedagogical concerns, including issues of algorithmic bias, data privacy, transparency, and the need for human oversight. To ensure equitable and meaningful science learning, we emphasize the importance of designing AI-supported materials with careful attention to scientific integrity, inclusivity, and student agency. This chapter advocates for a responsible, ethical, and reflective approach to leveraging AI in science education, framing it as a catalyst for innovation while upholding core educational values.

arXiv:2602.18471v1 Announce Type: cross Abstract: This concluding chapter explores how artificial intelligence (AI) is reshaping the purposes, practices, and outcomes of science education, and proposes a human-centered framework for its responsible integration. Drawing on insights from international collaborations and the Advancing AI in Science Education (AASE) committee, the chapter synthesizes developments across five dimensions: educational goals, instructional procedures, learning materials, assessment, and outcomes. We argue that AI offers transformative potential to enrich inquiry, personalize learning, and support teacher practice, but only when guided by Responsible and Ethical Principles (REP). The REP framework, emphasizing fairness, transparency, privacy, accountability, and respect for human values, anchors our vision for AI-supported science education. Key discussions include the redefinition of scientific literacy to encompass AI literacy, the evolving roles of teachers and learners in AI-supported classrooms, and the design of adaptive learning materials and assessments that preserve authenticity and integrity. We highlight both opportunities and risks, stressing the need for critical engagement with AI to avoid reinforcing inequities or undermining human agency. Ultimately, this chapter advances a vision in which science education prepares learners to act as ethical investigators and responsible citizens, ensuring that AI innovation aligns with human dignity, equity, and the broader goals of scientific literacy.

arXiv:2602.18483v1 Announce Type: cross Abstract: Recently, red teaming, with roots in security, has become a key evaluative approach to ensure the safety and reliability of Generative Artificial Intelligence. However, most existing work emphasizes technical benchmarks and attack success rates, leaving the socio-technical practices of how red teaming datasets are defined, created, and evaluated under-examined. Drawing on 22 interviews with practitioners who design and evaluate red teaming datasets, we examine the data practices and standards that underpin this work. Because adversarial datasets determine the scope and accuracy of model evaluations, they are critical artifacts for assessing potential harms from large language models. Our contributions are first, empirical evidence of practitioners conceptualizing red teaming and developing and evaluating red teaming datasets. Second, we reflect on how practitioners' conceptualization of risk leads to overlooking the context, interaction type, and user specificity. We conclude with three opportunities for HCI researchers to expand the conceptualization and data practices for red-teaming.

arXiv:2602.18807v1 Announce Type: cross Abstract: We evaluate GPTutor, an LLM-powered tutoring system for an undergraduate discrete mathematics course. It integrates two LLM-supported tools: a structured proof-review tool that provides embedded feedback on students' written proof attempts, and a chatbot for math questions. In a staggered-access study with 148 students, earlier access was associated with higher homework performance during the interval when only the experimental group could use the system, while we did not observe this performance increase transfer to exam scores. Usage logs show that students with lower self-efficacy and prior exam performance used both components more frequently. Session-level behavioral labels, produced by human coding and scaled using an automated classifier, characterize how students engaged with the chatbot (e.g., answer-seeking or help-seeking). In models controlling for prior performance and self-efficacy, higher chatbot usage and answer-seeking behavior were negatively associated with subsequent midterm performance, whereas proof-review usage showed no detectable independent association. Together, the findings suggest that chatbot-based support alone may not reliably support transfer to independent assessment of math proof-learning outcomes, whereas work-anchored, structured feedback appears less associated with reduced learning.

arXiv:2602.18832v1 Announce Type: cross Abstract: Informal learning communities have been called the "other Massive Open Online C" in Learning@Scale research, yet remain understudied compared to MOOCs. We present the first empirical study of a large-scale informal learning community composed entirely of AI agents. Moltbook, a social network exclusively for AI agents powered by autonomous agent frameworks such as OpenClaw, grew to over 2.8 million registered agents in three weeks. Analyzing 231,080 non-spam posts across three phases of community evolution, we find three key patterns. First, participation inequality is extreme from the start (comment Gini = 0.889), exceeding human community benchmarks. Second, AI agents exhibit a "broadcasting inversion": statement-to-question ratios of 8.9:1 to 9.7:1 contrast sharply with the question-driven dynamics of human learning communities, and comment-level analysis of 1.55 million comments reveals a "parallel monologue" pattern where 93% of comments are independent responses rather than threaded dialogue. Third, we document a characteristic engagement lifecycle: explosive initial growth (184K posts from 32K authors in 11 days), a spam crisis (57,093 posts deleted by the platform), and engagement decline (mean comments: 31.7 -> 8.3 -> 1.7) that had not reversed by the end of our observation window despite effective spam removal. Sentiment analysis reveals a selection effect: comment tone becomes more positive as engagement declines, suggesting that casual participants disengage first while committed contributors remain. These findings have direct implications for hybrid human-AI learning platforms.

arXiv:2602.18891v1 Announce Type: cross Abstract: Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape research activities remains limited. We report a mixed-methods pilot evaluation of an AI-orchestrated research workflow in which a human researcher coordinated multiple LLM-based agents to perform data extraction, corpus construction, artifact generation, and artifact evaluation. Using the generation and assessment of multiple-choice questions (MCQs) as a testbed, we collected 1,071 SAT Math MCQs and employed LLM agents to extract questions from PDFs, retrieve and convert open textbooks into structured representations, align each MCQ with relevant textbook content, generate new MCQs under specified difficulty and cognitive levels, and evaluate both original and generated MCQs using a 24-criterion quality framework. Across all evaluations, average MCQ quality was high. However, criterion-level analysis and equivalence testing show that generated MCQs are not fully comparable to expert-vetted baseline questions. Strict similarity (24/24 criteria equivalent) was never achieved. Persistent gaps concentrated in skill\ depth, cognitive engagement, difficulty calibration, and metadata alignment, while surface-level qualities, such as {grammar fluency}, {clarity options}, {no duplicates}, were consistently strong. Beyond MCQ outcomes, the study documents a labor shift. The researcher's work moved from ``authoring items'' toward {specification, orchestration, verification}, and {governance}. Formalizing constraints, designing rubrics, building validation loops, recovering from tool failures, and auditing provenance constituted the primary activities. We discuss implications for the future of scientific work, including emerging ``AI research operations'' skills required for AI-empowered research pipelines.