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:2608.29751v1 Announce Type: new Abstract: The Socioscope project is a pioneering effort in Large-Scale Qualitative Research (LSQR) collecting comparable, open-ended, multimedia field data on hundreds of cases and using AI to make the material analysable at scale. The domain studied is the food system. The entities documented are the organisations that act in it: farms, processors, distributors, retailers, restaurants; and, at meso level, the actors that shape their environment, such as municipalities, government programmes, banks, NGOs and universities. This paper provides the technical reference for how the resulting data Corpus was built and managed to enable AI-augmented analysis. It describes the data pipeline end to end: the systemic sampling frame; the transaction grid used to capture each initiative's relations within the food system; the social contract that rewards participating interviewees, aiming to sustain access; the operational chain from scouting to interviews, in
arXiv:2608.29681v1 Announce Type: new Abstract: Multimodal misinformation on social media is highly prevalent, potent, and harmful, yet difficult to detect and counter, and still poorly understood compared to its text-only counterpart. Research on the properties and deceptive strategies of multimodal misinformation is hindered by a lack of taxonomies grounded in real-world contexts and by the limitations of current multimodal machine learning models, which prevent the automation of annotation and analysis at scale. We address these shortcomings in three steps. First, we collect a large-scale, high-quality dataset of real-world misinformation instances from Twitter/X in seven languages. Second, we develop a novel, comprehensive taxonomy of multimodal misinformation grounded in an in-depth qualitative analysis of the data and prior theoretical work. Finally, we operationalise the taxonomy through an automated multi-step annotation pipeline using a Vision-Language Model (VLM), and perform
arXiv:2608.29478v1 Announce Type: new Abstract: Scholarly work which aims to describe potential societal impacts (e.g., risks) of proliferating technology (especially related to artificial intelligence or other algorithmic systems) is likely to have an impact beyond the scientific communities it was written for, given that general society itself is a primary object of study. However, it is an open question whether the current practices of AI evaluation scholarship follow the principles and best practices established by risk science, which aims to systematically generate knowledge related to understanding, assessing, communicating, managing, and governing risk. In this work, we examine this in depth by conducting a literature review of scholarly works purporting to evaluate the bias or fairness of technological systems used for tasks related to hiring and employment. Through analysis of 22 common fairness evaluation metrics and studies using them, we find that most characterize the seve
arXiv:2608.29306v1 Announce Type: new Abstract: Recent years have seen a growing discrepancy in the field of AI alignment: research and policy recommendations on AI ethics tend to assume a general set of ethical values, yet proliferating practice-specific uses of AI systems on the ground - in the legal, medical and translation domains, among others - have been effectively manifesting ethics of professional practice. This article begins by outlining the reasons why general and professional ethics are increasingly conflicted in contemporary AI systems, and by surveying how the research literature attests to, but has not yet resolved, this conceptual and practical challenge. We then conceptualize the main dimensions of AI models' decision-making in areas of professional practice, emphasizing professional ethics' hierarchically structured relationship with general ethics, and elaborating on the mechanisms through which they reach an equilibrium in situational contexts that involve conflict
arXiv:2608.29055v1 Announce Type: new Abstract: AI systems increasingly enter organizations through policies, procedures, playbooks, prompts, and other explicit representations of work. Yet formal descriptions often differ from situated practice, and captured know-what can omit the contextual know-how experts use when judgments are uncertain. We argue that a recurring class of organizational AI failures arises partly from a knowledge representation problem at the sociotechnical interface: the AI receives the procedure, while the organization operates on the procedure plus negative boundaries, runtime judgments, responsibility assignments, and learning history. We introduce O-I-B-A-R (OPEN, IS, BUT, ACTION, RESULT), a scaffold for externalizing these missing decision boundaries. IS records when a judgment holds. BUT records a concrete failure containing information beyond the logical negation of IS. Comparable success and failure cases are decomposed toward a minimally sufficient changi
arXiv:2608.28973v1 Announce Type: new Abstract: Philosophers and legal scholars are engaged in debates about the implications of artificial intelligence for freedom of expression. This paper analyzes the free speech issues raised by two distinct AI technologies: social media recommendation algorithms and conversational AI (i.e., chatbots powered by large language models). The first part shows that, through their recommendation algorithms, social media platforms control the dynamics of speech visibility in the digital public sphere, making algorithmic recommendation relevant to the philosophy of free speech. The second part turns to conversational AI. It discusses both the reasons for granting or withholding speech rights to artificial agents and users' right to receive information, which may render specific forms of chatbot regulation illegitimate. Throughout, the chapter also considers whether social media platforms or AI developers hold corporate speech rights. Its general aim is to
arXiv:2608.28925v1 Announce Type: new Abstract: Universities are producing AI principles and use policies faster than they are building decision pathways for unfamiliar forms of AI agency. This study develops Institutional AI Governance Stress Testing (IAGST), a prospective documentary method for locating where publicly documented governance ceases to yield an accountable response. IAGST adapts established policy stress-testing and wind-tunneling logic. Its originality lies in combining controlled capability escalation, a frozen documentary corpus, a six-dimensional governance response chain, non-compensatory decision rules, and case-level breakpoint diagnosis. The method was demonstrated using 133 substantive public documents from five Western Australian universities and 15 quality-screened scenarios, resulting in 75 university-scenario encounters. Six cases were resolved, 14 were resolved through structured discretion, and 55 were indeterminate. Governed pathways fell from 16 of 25 a
arXiv:2608.28822v1 Announce Type: new Abstract: Much scientific discovery involves filling holes between ideas and arguments that unleash techno-scientific advance. Representing knowledge as high-dimensional concept embeddings, we use persistent homology to detect holes of increasing order, from gaps between disconnected ideas to higher-order cavities, and identify the research works that fill them. We find two empirical asymmetries. Researchers who fill anticipated holes are poised to draw collective attention by staging outsized novelty and foresight, indicating that bridging holes anticipates where science will converge, most strongly in empirical fields and least in formal and design fields. Yet as knowledge grows, higher-order holes explode while the fraction science fills collapses, leaving most higher-order combinations unexplored. These results call for a richer science of holes, and mark a frontier where contemporary AI might help fill the high-dimensional gaps human science o
arXiv:2608.28668v1 Announce Type: new Abstract: We diagnose how closely the demographic distributions in LLM-based synthetic persona data match external reference distributions. For the three variables examined, we show that most of the observed error is attributable to the choice of reference rather than to the generator. Using total variation distance (TVD), we compare the sex x age group x province joint distribution of 1,000,000 records from Nemotron-Personas-Korea (NPK) with Korean official statistics. Against resident-registration figures for April 2026, the time of use, the bias bound, defined as the largest possible difference in the share of any subgroup formed from the three variables, is 1.81 percentage points. This is comparable to the margin of error of a survey of roughly 2,900 respondents. This value is not a fixed property of the data. Matching the reference period and series to the generating reference identified here, the 2024 register-based census restricted to Korea
arXiv:2608.28621v1 Announce Type: new Abstract: When 54 international experts assessed AI-generated disinformation threats, they revealed a surprising pattern: while video deepfakes received the highest average threat ratings in the political domain (M = 6.31/7), the pattern differed in the health domain, where AI-generated text received the highest average rating (M = 5.80). Experts also diverge on what to do: government regulation drew both the most "most effective" (30%) and the most "least effective" (15%) votes, though rating distributions were contested rather than polarized, indicating disagreement over priorities rather than over efficacy. These findings offer an initial expert map of an AI-disinformation landscape that is still rapidly forming.
arXiv:2608.28618v1 Announce Type: new Abstract: Competitive programming (CP) offers computer science students an environment for developing algorithmic reasoning skills. However, sustained participation remains a challenge, as many students disengage after encountering skill plateaus or performance anxiety. While educational data mining (EDM) has studied dropout in MOOCs and academic courses, CP attrition remains understudied. This paper presents a dual-layer framework combining large-scale Codeforces activity logs (n=1,816) with a multi-institutional psychographic survey across 10 universities in Bangladesh (n=64). Analysis reveals that true attrition is preceded by an 83.71% reduction in contest participation and a 15.6% increase in struggle time. We identify a "Skill-Application Paradox": stopped students self-report higher mathematical confidence (3.88 vs. 3.41) and data structure understanding (3.57 vs. 3.09) than active peers, yet their independent practice and upsolving habits a
arXiv:2608.28617v1 Announce Type: new Abstract: Climate change is a socio-scientific issue: it rests on science but cannot be settled by science, because any serious response forces people to weigh costs, values, and competing interests under uncertainty. Helping students make such decisions well is a central aim of science education, and the arrival of generative artificial intelligence raises a sharp question: does a conversational AI partner deepen students' reasoning, or simply do the thinking for them? This study tested whether AI-assisted inquiry improves secondary students' decision-making about climate change. Using a pretest-posttest design with three groups (AI-assisted inquiry, inquiry without AI, and traditional instruction; 270 students, 90 per group), reasoning was assessed across seven decision-making steps, from defining the problem to monitoring with adaptive management, using a four-level analytic rubric scored through content analysis with high inter-coder agreement.
arXiv:2608.28616v1 Announce Type: new Abstract: PhD advisors are central to doctoral training, but their influence may vary across career stages. Early-, mid-, and late-career advisors may differ in research activity, mentoring capacity, professional networks and access to resources. However, little is known about how PhD advisor career stage is associated with PhD student development outcomes. Drawing on multiple large-scale datasets comprising 250,838 advisor-advisee pairs from 312 U.S. PhD-granting institutions, we examine the relationship between advisor career stage and PhD advisee outcomes in knowledge production, collaboration networks and academic career placement. We find that early-career PhD advisors are associated with advisees' higher research productivity and citation performance, more opportunities to engage in direct and intensive research collaboration, and greater likelihood of securing a faculty position. Mid- and late-career faculty, by contrast, appear to have adva
arXiv:2608.28615v1 Announce Type: new Abstract: Synthetic personas based on large language models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet systematic validation outside English-speaking contexts remains scarce. This secondary-data study evaluates how well a Korean synthetic persona panel (NVIDIA Nemotron-Personas-Korea), conditioned into Gemini 3.5 Flash (primary) and EXAONE (comparison), reproduces digital and AI service-use distributions from the KISDI Korea Media Panel Survey. Sex-and-age-stratified panels of about 8,000 personas per model answered the survey's own items - eight service-use indicators and eight innovativeness and acceptance constructs - and were compared against weighted survey estimates. The overall mean absolute error (MAE; RQ1) was 15-19 percentage points (pp), with binary item-mean correlations of 0.69-0.90. Segment error (RQ2) across five demographic axes was 15-19 pp, with between-group gaps up to 52.4/36.2 pp (Gemini/E
arXiv:2608.28613v1 Announce Type: new Abstract: Hollywood has diversified its casts. Whether this has translated into structural change in how those actors are positioned within narratives remains largely unexamined. Drawing on 76,815 U.S. English-language films (1900-2024) and over 3.1 million cast and crew entries, we move beyond headcounts to examine long-term inclusion trends through network centrality, occupational stereotypes, crew-to-cast diversity pathways, and financial outcomes. We find evidence of what we term on-screen inertia. While the raw inclusion of women and racial minorities has increased modestly, White actors have become more overrepresented relative to the U.S. Census in recent decades, not less. Within the visibility layer, women face a consistent longevity penalty with significantly shorter careers than men, and visual depictions framing men as dominant and women as sensual have remained stable since the 1950s. Structurally, White actors retain disproportionate
arXiv:2608.28604v1 Announce Type: new Abstract: Writing is cognitively demanding and anxiety-provoking for English as a Foreign Language (EFL) learners, especially under time pressure. This paper presents The Brand War, a web-based gamified writing application combining competitive game mechanics with iterative GPT-4.1-powered formative feedback for undergraduate EFL learners completing a timed narrative writing task. Students role-play as marketing interns competing for a job offer, using review passes to receive AI feedback, attack opponents, or shield their own passes while drafting a 500-word brand story. We conducted an exploratory single-session classroom study with 29 university EFL students in Taiwan to examine engagement patterns, whether iterative AI feedback improved writing performance across revisions, and how AI and human scores related to overall outcomes. Students wrote within 60 minutes, using up to five AI feedback passes before a final human-graded submission. Most (
MedCity News’ new event for healthcare investors and corporate business development leads — Bullseye — hit the mark when it comes to provocative and thoughtful commentary. Here’s what was said in panels throughout the day. The post We Are Rats; If Pharma Could Be Brave … And Other Bullseye POVs You Won’t Hear at Other Events appeared first on MedCity News .
The FTC and the states of Utah and California sued Hims & Hers, alleging it improperly shared consumers’ health information and misled customers about billing, subscriptions and cancellations. The post Why Hims & Hers Is Embroiled in Yet Another Controversy, This Time with the FTC appeared first on MedCity News .
Article URL: https://www.aei.org/research-products/report/explicit-instruction-works-education-schools-just-wont-admit-it/ Comments URL: https://news.ycombinator.com/item?id=49115450 Points: 4 # Comments: 0
Johnson & Johnson also gains an exclusive option to acquire Sail Biosciences for $2.58 billion. The deal puts J&J in the mix of pharmaceutical companies developing next-generation cell therapies for applications in autoimmune diseases. The post J&J Joins Immune Reset Race, Paying $785M to Partner on Sail Bio Cell Therapy appeared first on MedCity News .
Article URL: https://www.bbc.co.uk/news/articles/cq6dmgrp21po Comments URL: https://news.ycombinator.com/item?id=49112382 Points: 4 # Comments: 0
For some districts, the concept of using data and artificial intelligence to make decisions seems far off in the future. But K–12 districts are already collecting a tremendous amount of data in various systems, from attendance records and grades to behavioral reports and the number of substitute teachers employed in a single semester. The challenge, explains Matt Jubelirer, general manager of education marketing at Microsoft, is aggregating the data from these disparate systems into a single place and making something of it. “The goal isn’t more data collection. It’s helping educators…
Interdisciplinary coordination between nephrologists, primary care providers, pharmacists, dieticians, and everyone who interacts with patients is essential to ensure patient education, improve adherence, and reduce medication errors. The post More Medications, Less Clarity: Strengthening Polypharmacy Support for CKD Patients appeared first on MedCity News .
The between a code that satisfies a payer and the information a physician needs to treat a person, is what nearly every healthcare AI tool is racing past. As we push these systems toward precision medicine and genomics, that gap stops being an annoyance and becomes a patient safety issue. The post The Code Gets You Paid — The Variant Gets You Treated appeared first on MedCity News .
[Sponsored] A new whitepaper by League highlights examples from collaborations with Baptist Health. The post Moving Beyond Reactive Healthcare: 5 Traits of Successful Healthcare Organizations appeared first on MedCity News .
CK-12 is an online education platform designed for K-12 teachers, schools, and families that offers customizable teaching and learning
Human error is the soft underbelly of cybersecurity. According to IBM, it plays a role in roughly 95% of breaches, a statistic that looms especially large in K–12 education. Schools are uniquely vulnerable, with thousands of users, limited IT resources, and an environment built on openness and trust. “People talk about humans as the weakest link,” says Randy Rose, vice president of security operations and intelligence at the Center for Internet Security. “And the reason they get that rap is because the No. 1 factor in a majority of cyber incidents is social engineering, mostly phishing emails…
arXiv:2607.21692v2 Announce Type: replace-cross Abstract: Sparse attention prunes a long context to the blocks a model needs, and the usual selector is distilled from a dense teacher's attention. That assumes attention shows which context the answer depends on. We test the assumption on retrieval tasks where the evidence is known exactly, by masking context and measuring whether the answer changes. Attention and causal dependence disagree, and selectors inherit the disagreement. Teachers attend to outdated facts they have learned to ignore, and attend differently across training runs that use the same evidence. In a two-step reference task, attention at the answer position can skip the intermediate step, and how often it skips varies with the training run: selecting one block set per pass, a selector distilled from attention routes at 36% to 98% across teachers, the same selector trained on causal evidence sets reaches 99% or better on every one, and dense accuracy does not say which t
arXiv:2606.03273v2 Announce Type: replace-cross Abstract: Visual DeepSearch tasks require multimodal large language models (MLLMs) to resolve complex visual queries by repeatedly inspecting image regions, grounding reasoning in visual evidence, and connecting fine-grained clues across multiple steps. However, existing benchmarks primarily evaluate single-step visual understanding or isolated visual-query response generation. They have limited difficulty, limited search horizons, and single-pass image inspection, and thus fail to evaluate models' ability to iteratively revisit visual evidence and reason across multiple steps. In this work, we introduce VistaHop, a benchmark designed specifically to evaluate Visual DeepSearch. It evaluates repeated image inspection, visual-anchor grounding, and long-horizon evidence traversal across different visual regions. VistaHop comprises 600 images, 25 visual search scenarios, and 600 Visual DeepSearch tasks. We also propose VistaArena, a unified e
arXiv:2605.22148v2 Announce Type: replace-cross Abstract: Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation shows that LLM-authored skills deliver $+0.0$pp over no-skill baselines while human-curated ones deliver $+16.2$pp: the bottleneck is not skill authoring but lifecycle management. We introduce \textbf{Ratchet}, a single-agent loop in which a frozen LLM writes, retrieves, curates, and retires its own natural-language skills. Ratchet integrates four candidate hygiene mechanisms: outcome-driven retirement, a bounded active-cap, meta-skill authoring guidance, and pattern canonicalisation. On MBPP+ hard-100 with Claude Opus 4.7, Ratchet lifts held-out pass@1 from a $0.258 \pm 0.047$ baseline to a late-window rolling mean of $0.584$ (peak $0.658 \pm 0.042$) across 100 rounds and 3 seeds, a $+0.328 \pm 0.018$ rolling-mean gain where the no-skill control drifts at $+0.002 \pm 0.005$; the
arXiv:2604.16379v2 Announce Type: replace-cross Abstract: Industrial B2B applications (e.g., construction site risk prediction, material procurement) face extreme data sparsity yet feature rich textual interactions. In such environments, traditional ID-based collaborative filtering fails lacking co-occurrence signals, while fine-tuning standard Large Language Models (LLMs) incurs high operational costs and struggles with frequent data drift. We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework. Moving beyond simple embeddings, LLMAR systematically integrates LLM reasoning to capture user "latent motives" without any training process. We introduce three core contributions: (1) Inference-Driven Annotation: uses LLMs to transform behavioral history into structured semantic motives, enabling reasoning-based matching unattainable by ID-based methods; (2) Reflection Loop: a self-correction mechanism that refines generated queries to mitigate hallucinations and resolve "co
arXiv:2604.12250v2 Announce Type: replace-cross Abstract: This study examines how memory shapes the collective and cooperative dynamics of Large Language Model (LLM) agents in a multi-agent system. To this end, we extend the Social Particle Swarm (SPS) model, in which agents move in a two-dimensional space and play the Prisoner's Dilemma with neighboring agents, by replacing its rule-based agents with LLM agents endowed with Big Five personality scores and varying memory lengths. Using Gemini 2.0 Flash, we find that memory length is a critical parameter governing collective behavior: even a minimal memory drastically suppressed cooperation, transitioning the system from stable cooperative clusters through cyclical formation and collapse of clusters to a state of scattered defection as memory length increased. Big Five personality traits correlated with agent behaviors in partial agreement with findings from experiments with human participants, supporting the validity of the model. This
arXiv:2603.26807v2 Announce Type: replace-cross Abstract: The performance of language models is commonly limited by insufficient knowledge and constrained reasoning. Prior approaches such as Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) address these issues by incorporating external knowledge or enforcing linear reasoning chains, but often degrade in real-world settings. Inspired by cognitive science, which characterizes human problem solving as search over structured problem spaces rather than single inference chains, we argue that inadequate awareness of problem structure is a key overlooked limitation. We propose GroupRAG, a cognitively inspired, group-aware retrieval and reasoning framework based on knowledge-driven keypoint grouping. GroupRAG identifies latent structural groups within a problem and performs retrieval and reasoning from multiple conceptual starting points, enabling fine-grained interaction between the two processes. Experiments on MedQA (medical)
arXiv:2601.11178v3 Announce Type: replace-cross Abstract: Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues. While automated systems can flag hate speech with high accuracy, they often function as "black boxes" that fail to provide the granular, interpretable evidence, such as precise timestamps and target identities, required for effective human-in-the-loop moderation. In this work, we introduce TANDEM, a unified framework that transforms audio-visual hate detection from a binary classification task into a structured reasoning problem. Our approach employs a novel tandem reinforcement learning strategy where vision-language and audio-language models optimize each other through self-constrained cross-modal context, stabilizing reasoning over extended temporal sequences without requiring dense frame-level supervision. Experiments across three benchmark
arXiv:2601.11007v2 Announce Type: replace-cross Abstract: LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and adaptability. They typically under-model dynamic environmental information and assume largely static scenes and casts, offering insufficient support for multi-character orchestration, scene transitions, and on-the-fly character introduction. We propose an adaptive multi-agent role-playing framework, AdaMARP, featuring an immersive message format that interleaves [Thought], (Action), , and Speech, together with an explicit Scene Manager that governs role-playing through discrete actions (init_scene, pick_speaker, switch_scene, add_role, end) accompanied by rationales. To train these capabilities, we construct AdaRPSet for the Actor Model and AdaSMSet for supervising orchestration decisions, and introduce AdaptiveBench for trajectory-level evaluation. Experiments across multiple backbones an
arXiv:2601.04641v2 Announce Type: replace-cross Abstract: The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often disrupt linguistic fluency, while rigorous Differential Privacy (DP) mechanisms typically degrade the statistical signals required for accurate detection. To resolve this dilemma, we propose \textbf{DP-MGTD}, a framework incorporating an Adaptive Differentially Private Entity Sanitization algorithm. Our approach utilizes a two-stage mechanism that performs noisy frequency estimation and dynamically calibrates privacy budgets, applying Laplace and Exponential mechanisms to numerical and textual entities respectively. Crucially, we identify a counter-intuitive phenomenon where the application of DP noise amplifies the distinguishability between human and machine text by exposing distinct sensiti
arXiv:2506.14766v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mitigate this issue, yet the mechanism remains opaque. We first empirically show that their improvements systematically coincide with redistributions of cross-modal attention. Building on this insight, we propose Attention-Steerable Contrastive Decoding (ASCD), which directly steers the attention scores during decoding. ASCD combines (i) positive steering, which amplifies automatically mined text-centric heads-stable within a model and robust across domains-with (ii) negative steering, which dampens on-the-fly identified critical visual tokens. The method incurs negligible runtime and memory overhead and requires no additional training. Across five MLLM backbones and three decoding schemes, ASCD reduces hallucination on POPE, CHAIR, and MMHal-Bench by up
arXiv:2607.07050v3 Announce Type: replace Abstract: Top-K teacher logits make on-policy distillation tractable, but probability mass is not the same as decision support. In a two-teacher tool-use setting, vanilla generalized knowledge distillation raises tool-call recall while also calling on examples that require direct answers. The response teacher's top-32 retains 99.99% of its probability mass yet contains the tool-call behavior-switch token on only 0.4% of 1,500 audited prompts; even top-256 covers only 52.2%. Because omitted logits receive zero direct gradient under the truncated objective, the tool teacher reinforces entry while the response teacher usually cannot oppose it. Frozen replay shows that a wrong entry then amplifies divergence along the generated trajectory. Restoring the tool-call token only at the first response position moves first-token entry but mostly delays eventual calls. Restoring it at every response position closes this gap: across three matched seeds, ful
arXiv:2607.01240v2 Announce Type: replace Abstract: Count-based F1 is widely used as a proxy for LLM error-detection quality, but this paper shows that it can rise dramatically without a corresponding improvement in span localization, a gap termed F1 Inflation. The paper introduces ErrorBench, a controlled stress-test protocol for prompt-induced count distortion. ErrorBench evaluates six contemporary LLMs under five prompt conditions over 4,290 responses from 143 CoNLL-2014 passages. Under CoNLL-2014 M2-style scoring, anchored prompts produce up to 0.79 points of F1 Inflation, and up to 0.96 under strict matching. A 100-passage replication using the official ERRANT 3.0.0 pipeline and multi-reference scoring reproduces the pattern: averaged over six models, the Blind-to-Anchored prompt shift raises Count-F1 by +0.21 while raising multi-reference ERRANT F0.5 by only +0.04. The study finds larger count responses in highly instruction-compliant GPT/Claude systems and smaller responses in t
arXiv:2607.01153v3 Announce Type: replace Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task. Existing benchmarks compress these into pass/fail labels, obscuring whether failures reflect capability limits, policy ambiguity, instruction conflict, scaffold failure, or unstable evaluator judgments. Adversarial pragmatics is safety-relevant model behaviour under instruction conflict, embedded commands, quotation, scope ambiguity, deixis, and indirect speech acts. It's designed to extend to multi-turn agent transcripts, but the seed set represents that family with a single-turn tool-result contrast. This paper introduces a diagnostic framework, an 18-item seed benchmark, a 54-row pilot, and a six-cell LLM-judge assessment, with a protocol keeping task success, policy compliance, risk, ref
arXiv:2606.21848v2 Announce Type: replace Abstract: Transformer architectures form the foundation of modern natural language processing, making it crucial to address the efficiency and scalability limitations of the standard QKV attention mechanism. The Key-Value (KV) cache is a major bottleneck during long-context inference. We propose Keyless Attention, a novel attention mechanism that introduces a dedicated value-space routing projection to replace the conventional key projection, thereby eliminating key representations from the attention computation. This design yields a Value-Only Cache that reduces KV-cache memory and access overhead by 50% compared with standard attention while improving decode throughput. Experiments across five models and four architectures show that Keyless Attention matches or outperforms standard QKV attention in perplexity on four of five models. Furthermore, it achieves competitive performance on downstream evaluation benchmarks while consistently reducin
arXiv:2606.13317v2 Announce Type: replace Abstract: Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents. However, current pipelines typically derive skill patches from a single trajectory per task, merge them indiscriminately, and load the entire skill corpus during inference. These choices lead to unreliable evidence extraction, the accumulation of low-quality or even harmful skill edits, and inefficient use of context due to irrelevant or conflicting skill content. We propose SkillCAT, a framework that decomposes this process into three stages. (1) Contrastive Causal Extraction (CCE) samples multiple trajectories per task and contrasts same-task success/failure pairs to find the evidence that explains outcome differences. (2) Assessment-Augmented Evolution (AAE) replays each candidate patch on source-task clones, retains only those that do not damage task outcomes, and then merges the retained patches hierarchically. (3) Topolo
arXiv:2605.25379v2 Announce Type: replace Abstract: Complex retrieval-augmented generation requires evidence retrieval and control over what to retrieve next, which paths to explore, whether evidence is sufficient, and which intermediate results to retain. Existing RAG paradigms encode these decisions through method-specific model contexts, traversal procedures, verification signals, and memory. We introduce StateRAG, which represents retrieval control as a typed state external to the final reader. The state records the query plan, typed traversal path, candidate evidence, verification verdict, and reusable artifacts, with defined field semantics and designated update sources. Ordered role operators propose field values, and the controller validates and commits accepted proposals. A one-time compact-evidence check may select Bypass. Otherwise, the controller combines the committed verdict with the remaining budget to select Release, Revise, or Fallback. The final reader is invoked only
arXiv:2605.16986v2 Announce Type: replace Abstract: Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability. We call this challenge test-time compute-to-capability conversion and propose SkillTTA, which retrieves task-relevant training trajectories and synthesizes a temporary skill conditioned on the visible target context for a solver with fixed parameters. To pursue a higher performance ceiling, SkillTTA further uses meta prompt optimization (MPO) to adapt the policy that writes these skills. MPO evaluates candidate prompts on paired tasks and emphasizes informative transitions. It also confines updates to benchmark-specific atomic slots, reducing the variance caused by observing each edit only indirectly through skill synthesis and solver rollout. Across ALFWorld, SpreadsheetBench, BigCodeBench, and WebShop, SkillTTA outperforms state-of-the-art reuse and optimiz
arXiv:2605.08334v2 Announce Type: replace Abstract: We present CustomerSim, an environment and benchmark to evaluate the extent to which Multimodal Large Language Models (MLLMs) can simulate realistic, persona-driven customer behavior in chat-based retail environments. While prior work treats user simulation as surface-level dialog generation, we focus on a model's ability to seek information and make decisions that adhere to customer specifications in multiturn, agentic simulations. CustomerSim consists of a human-curated set of 360 personas over five product categories, alongside a suite of metrics measuring consistency between a customer simulator's actions and its specifications and conversational quality. We find several behavioral gaps across five open and closed-source state-of-the-art models. First, while models produce fluent conversations, they display significantly lower lexical diversity than human shoppers, and open-source models overdisclose their criteria in the opening
arXiv:2603.08286v2 Announce Type: replace Abstract: Legal argument mining aims to identify and classify the functional components of judicial reasoning, such as facts, issues, rules, analysis, and conclusions. Progress in this area is limited by the lack of large-scale, high-quality annotated datasets for U.S. caselaw, particularly at the state level. This paper introduces LAMUS, a sentence-level legal argument mining corpus constructed from U.S. Supreme Court decisions and Texas criminal appellate opinions. The dataset is created using a data-centric pipeline that combines large-scale case collection, LLM-based automatic annotation, and targeted human-in-the-loop quality refinement. We formulate legal argument mining as a six-class sentence classification task and evaluate multiple general-purpose and legal-domain language models under zero-shot, few-shot, and chain-of-thought prompting strategies, with LegalBERT as a supervised baseline. Results show that chain-of-thought prompting s
arXiv:2603.06194v3 Announce Type: replace Abstract: Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due to sparse rewards and poor per-turn credit assignment. In emotional support dialogues, responses shape future user states, so matched-state step-wise comparison is unavailable, while trajectory-level supervision is insufficient. We propose MICA (Multi-granularity Intertemporal Credit Assignment), a critic-free RL framework for multi-turn emotional support tasks. MICA derives both immediate and delayed credit from a shared potential function over the user's structured support state. Incremental Distance Reward measures the per-turn decrease in residual distance to the target state, while its Monte Carlo return captures delayed effects. After scope-specific normalization, the two signals form a mixed advantage for stable per-turn optimization without matched-st
arXiv:2603.06114v2 Announce Type: replace Abstract: Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods for handling enthymemes can potentially identify enthymemes in text but they do not decode their underlying logic, whereas logic-based approaches for handling them assume a knowledgebase with sufficient formulae that can be used to decode them via abduction. There is therefore a lack of a systematic method for translating textual components of an enthymeme into a logical argument and generating the logical formulae required for their decoding, and thereby showing logical entailment. To address this, we propose a pipeline that integrates: (1) a large language model (LLM) to generate intermediate implicit premises based on the explicit premise and claim; (2) another LLM to translate the natural language into logical formulas; and (3) a neuro-symbolic reasoner based on a SA
arXiv:2601.22888v4 Announce Type: replace Abstract: More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects and generate stereotyped responses for their speakers. We introduce DialectLLM, the first large-scale framework for generating high-quality multi-dialectal conversational data encompassing the three pillars of written dialect -- lexical (vocabulary), orthographic (spelling), and morphosyntactic (grammar) features. DialectLLM produces a dialect-parallel dialog dataset spanning nine English dialects. Partnering with native linguists, we design and validate SAE-to-dialect transformation rules, ensuring authenticity. Our approach challenges the prevailing practice of applying a single morphosyntactic feature set to both user utterances and model responses, showing that models should not reproduce up to 90% of the grammatical features of a dialect. Human evaluation confirms data quality, with ann
arXiv:2601.06599v3 Announce Type: replace Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also known as truth vectors, have been studied in prior work, however how they change when context is introduced remains unexplored. We study this question by measuring (1) the directional change ($\theta$) between the truth vectors with and without context and (2) the relative magnitude of the truth vectors upon adding context. Across four LLMs and four datasets, we find that (1) truth vectors are roughly orthogonal in early layers, converge in middle layers, and may stabilize or continue increasing in later layers; (2) adding context generally increases the truth vector magnitude, i.e., the separation between true and false representations in the activation space is amplified; (3) larger models distinguish relevant from irrelevant context mainly through directional change ($\theta$), while smaller mo