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:2608.07297v1 Announce Type: new Abstract: Modern AI systems depend on annotated data, but annotation is rarely treated as the act of measurement that it is. Instead, annotation quality is commonly reduced to agreement: if multiple annotators assign the same annotation to a data instance, the annotations are taken to be high-quality. Yet agreement does not establish whether annotations validly capture the underlying concept they are meant to represent. In this paper, we argue that data annotation should be understood as a measurement problem. Like other forms of measurement, annotation requires defining a concept, operationalizing it through an instrument, applying that instrument, and evaluating the reliability and validity of the resulting measurements. Drawing on a literature review of annotation quality research (N=132) and semi-structured interviews with annotation team members (N=10), we develop a framework for diagnosing and correcting annotation issues. First, we map key d
arXiv:2608.06932v1 Announce Type: new Abstract: Educational short-video research spans disciplines, platforms and learning contexts, but the same label is applied to resources differing in function, activity, context and evaluation, complicating comparison and evidence synthesis. This study mapped the development, thematic organisation and operationalisation of educational short-video research. We analysed 2,169 records indexed in Web of Science and Scopus up to 11 June 2026 using bibliometric analysis, non-negative matrix factorisation topic modelling and structured content analysis. Publication output increased sharply from the mid-2010s but remained dispersed across outlets. Among 16 first-level topics, Skill Development in Educational Contexts was the largest, forming the structural core of the field, while topic overlap was predominantly pairwise. Video-Based Health Interventions for Attitude Change and Cognitive Load and Engagement in Instructional Video Design combined positive
arXiv:2608.06903v1 Announce Type: new Abstract: The rapid growth of artificial intelligence (AI) in music has expanded research from generation and information retrieval to education, health, and governance. Yet this growth does not necessarily imply balanced research attention. Where is research attention directed across diverse music tasks, and how can such imbalance be systematically measured? Existing studies examine AI music from separate technical, application-specific, or bibliometric perspectives, but lack a systematic framework for measuring field-level imbalance. To address this gap, we analyze 6,839 AI music publications from 2015 to April 2026 using a joint taxonomy of 12 application categories and 11 technical method families. We propose the Research Attention Profile, comprising four indicators of technical investment, method allocation, methodological diversity, and frontier-method adoption lag. Results show that technical support is concentrated in scalable, content-ori
arXiv:2608.06831v1 Announce Type: new Abstract: The harms in which AI is implicated range in nature and scope from unsafe user interactions through to the societal-wide consequences of AI adoption. Classification of the diverse risks of AI is foundational to AI governance: regulators, technology firms, and policymakers need structured accounts of risk upon which to act. Researchers and practitioners have accordingly developed many Sociotechnical Outcome Taxonomies (SOT). This paper presents an empirical study of SOT development and use, drawing on 25 interviews with researchers and practitioners across industry, academia, civil society, and government. We find SOT are weakly integrated into AI governance processes, and identify two features of SOT design and use that explain why. First, the design choices through which SOT produce structured representations of the complex problem space of AI risks tend to be invisible to downstream taxonomy users. Those users treat the resulting catego
arXiv:2608.06782v1 Announce Type: new Abstract: Prior research has established the importance of student instructor preferences and identified various influencing factors. However, the dynamics of how student instructor preferences develop and change are less well understood, due to the limitations of common course structures and reliance on one-time measurements. To bridge this gap, we utilize data from a novel learning platform that provides students with access to instructional content created by multiple instructors. This platform enables the quantification of preference emergence and evolution throughout an entire semester, as students repeatedly select content from different instructors. Examining both initial and final student instructor preferences suggests that preference is a dynamic construct continually shaped by experiences. Furthermore, our analysis of the associations between preferences and student characteristics reveals a nuanced picture: while student attributes did
arXiv:2608.06753v1 Announce Type: new Abstract: Office hour utilization in computer science courses can spike near deadlines, producing long wait times, frustrated students, and overworked staff. To address this problem, a large CS1 course implemented a split deadlines policy. Students were randomly divided into two groups with staggered release and due dates. Each group had the same amount of time to complete assignments, but the number of students with each due date was reduced by half. Our study evaluates the effectiveness of this policy. We measure office hour utilization and staff efficiency near deadlines, examine the policy's impact on student performance, and investigate student perception of the policy's fairness and effectiveness. Overall we found that the split deadline policy increased office hour efficiency, resulted in no significant difference in performance between groups, and was considered fair and effective by most students. Our experience report includes reflections
arXiv:2608.06572v1 Announce Type: new Abstract: Students learning to program benefit from access to large numbers of practice problems. Autograders are commonly used to support programming questions by providing quick feedback on submissions. But authoring accurate autograders remains challenging. Autograders are frequently created by enumerating test cases--a tedious process that can produce inaccurate autograders that fail to correctly classify submissions. When authoring accurate autograders is slow, it is difficult to create large banks of practice problems to support beginning programmers. We present solution-generated autograding: a faster, more accurate, and more enjoyable way to create autograders. Our approach leverages a key difference between software testing and autograding: The question author can provide a solution. By starting with a solution, we can eliminate the need to manually enumerate test cases, validate the autograder's accuracy, and evaluate other aspects of sub
arXiv:2608.06510v1 Announce Type: new Abstract: Agentic AI promises a more flexible form of digital agency: systems that can act on users' behalf, from filtering content to negotiating prices to selecting services. Whether it will empower users is an open question, and we argue that the answer depends on more than the technology. We conduct a comparative case analysis of four more mature domains where similar forms of agency arose: browser-based ad blockers, platform recommender systems, financial robo-advisors, and email spam governance. Across the cases, decisions about whose interests agents would serve were resolved through technical arrangements: API choices, protocol governance, industry standards, and default configurations. Beyond their technical form, these were political decisions. We identify this as depoliticization, a concept from political theory, here at work in technological systems. Its most consequential effect is that individual outcomes and collective contestation c
arXiv:2608.06472v1 Announce Type: new Abstract: Unmanned Aerial Vehicles are now widely used across business, government, and recreational contexts, creating new challenges for incident response and digital forensics. While previous forensics research has largely focused on the extraction of technical data from UAV systems, minimal empirical work has examined how UAV incidents are handled in real-world settings or what challenges incident handlers face during this response. To address this gap, this paper reports findings from an in-person focus group with UAV and counter-UAV practitioners from industry and government organizations in the United States. Using qualitative analysis, several key challenges are identified, including situational awareness and airspace visibility, fragmented reporting and interorganizational coordination, forensic and attribution limitations, legal and policy gaps, and shortfalls in training and operational capacity. The research extends socio-technical inci
Today, about 80 percent of K–12 students use computers or tablets at school--up from about 50 percent before the pandemic. Even as parents worry about too much “screen time,” schools are ramping it up.
One day, something clicked for Jacob Griffin's students. Mr. Griffin, a teacher at the NAF Academy of Engineering at Southeast Raleigh High School in North Carolina, found that students who had previously been going through the motions were coming to class more engaged, more driven, and more confident about the potential futures that lay beyond high school.
Researchers say a lack of reliable information on artificial intelligence use on campus could lead to misguided policies.
American schools spent roughly $30 billion on educational technology in 2024--a figure that's projected to nearly double by 2033. Superintendents are constantly bombarded with emails, brochures, and demos from education technology companies.
College admissions requirements keep K-12 tied to grades and Carnegie units, slowing competency-based and skills-first learning. The post The Tyranny of College Admissions: Why It’s So Challenging to Have Real Change in K-12 Education appeared first on Getting Smart .
AI plagiarism is becoming more and more common in and outside of the classroom.
Higher education is rapidly developing AI governance frameworks through the creation/modification of policies, establishing compliance structures, conducting procurement reviews, and developing acceptable use guidelines. The post Beyond compliance: Governing higher education in the age of intelligent systems appeared first on eCampus News .
Greenville, Wis – December 8, 2025 – School Specialty®, a leading provider of learning environments, supplies and science curriculum to ... Read more
The bell rings at 10:00 a.m. A teacher begins explaining quadratic equations. Some students lean forward, pencils ready. Others stare at the clock. A few are still turning yesterday’s lesson over in their minds.
Missouri’s largest charter-school sponsor entered August with nearly $3.3 million in its account, which is more than twice what it spent in the previous fiscal year. Now the Missouri Charter Public School Commission is sending some of that money back to the schools it oversees. At its August meeting, the commission approved $685,000 in rebates, […]
Early intervention based on accurate diagnosis of both metabolic risk factors and acute cardiac events could help make the difference between life and death for women. The post Advancing Women’s Heart Health Through Prevention and Rapid Diagnosis appeared first on MedCity News .
GSK gained rights to a Hutchmed antibody-targeted therapy conjugate, or ATTC. This new type of targeted therapy blocks two cancer-driving proteins and will initially be developed for lung, colorectal, and pancreatic cancers. The post GSK Pays $110M for Phase 1-Ready Hutchmed Asset in a New Class of Cancer Drugs appeared first on MedCity News .
At just 3 years old, Quintina Davis’ granddaughter, Juri, could name colors, numbers and shapes. Davis often heard from family and friends that Juri was smart and she should consider enrolling her granddaughter in preschool early. And a new literacy screening at one of her granddaughter’s primary care checkups confirmed it. In recent years, literacy […]
I’ve sat across from more than one district administrator staring at a dashboard full of reading intervention minutes and a flat progress line. The pattern is familiar: a student gets pulled for extra decoding practice, scores move for six or eight weeks, and then they stall — not because the student stopped trying, and not because the intervention stopped running.
What separates a student who can use a digital tool from one who can build something new with it? Kimberly Smith of Digital Promise argues that digital fluency, not just digital literacy, is the foundational skill K-12 career pathways have been missing. Drawing on credentialed cybersecurity programs in rural Alabama and a six-part fluency framework, this piece offers a clear, actionable case for why every career pathway, in every industry, must embed digital fluency now. The post Digital Fluency Is the Missing Foundation in K-12 Career Pathways appeared first on Getting Smart .
Public confidence in higher education sits at a new historic low, and colleges and universities are facing an identity crisis. On the one hand, a growing chorus of reformers argues that colleges should reorganize themselves entirely around preparing students for the labor market, perhaps with good reason. The post The false choice between citizenship and a first job appeared first on eCampus News .
We’re rounding up last week’s stories, from Antioch University’s fight against a "hostile takeover" to an IRS plan to punish diversity work.
I was supposed to be dancing, but instead I had been chatting incessantly. The teacher sat me under the piano so I could focus. From that tucked-away spot, I could see nothing but feet. Sneakers and socks sliding across the floor, heels lifting and landing in time with the music. “Focus on their feet,” he […] The post OPINION: Arts education can change lives, but we must invest in people who make it possible appeared first on The Hechinger Report .
Florida Bars Undocumented Students From Attending Public Universities Susan H. Greenberg Sun, 09/06/2026 - 10:31 PM Byline(s) Susan H. Greenberg Florida Bars Undocumented Students From Attending Public Universities Susan H. Greenberg Sun, 09/06/2026 - 10:31 PM Byline(s) Susan H. Greenberg
Florida Bars Undocumented Students from Attending Public Universities Susan H. Greenberg Sun, 09/06/2026 - 10:31 PM Byline(s) Susan H. Greenberg Florida Bars Undocumented Students from Attending Public Universities Susan H. Greenberg Sun, 09/06/2026 - 10:31 PM Byline(s) Susan H. Greenberg
Part of Nurse.org's Nurse Strike Intelligence data series, built on a proprietary database tracking a decade of U.S. registered-nurse strikes (2017–2026). Updated 8/7/26 Most hospitals never see a nurse strike.…
Nursing microbiology is a prerequisite course that teaches you about bacteria, viruses, fungi, and other microorganisms that cause disease in humans. Most nursing programs require it because the concepts you…
arXiv:2608.31082v2 Announce Type: replace-cross Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI is deploying LLM agents that reason over this data to answer complex questions for every knowledge worker. Agents can do this today, but at prohibitive cost. Each question repeatedly opens large documents to recover scattered evidence, consuming up to a million tokens. However, if the data were already structured, the same question would reduce to a cheap database lookup. For example, on FanOutQA benchmark, reasoning over an ideal pre-structured store is 28X cheaper, and the gap grows to orders of magnitude as questions fan out over more documents. Yet structuring everything in advance is not viable: documents hold vastly more possible structure than any workload will use, and the useful structure and documents are unknown until queries arrive. We propose agentic data cracking, a
arXiv:2605.29068v2 Announce Type: replace-cross Abstract: Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning. Reasoning-based guardrails significantly outperform classification-only baselines, but they incur substantial query latency and token overhead that make them impractical for highthroughput deployment. To address this challenge, we propose COLAGUARD, a guardrail model that transfers multi-step safety reasoning into a continuous latent space through a stage-wise training curriculum, enabling direct hidden-state propagation at inference. Evaluated on ten prompt- and response-moderation settings spanning eight safety benchmarks, COLAGUARD improves macro-F1 by 8.24 points over Llama Guard 3 and matches our explicit reasoning baseline, GuardReasoner, in macroF1 while delivering a 12.9X speedup and 2
arXiv:2605.02720v2 Announce Type: replace-cross Abstract: Vision-language models hold considerable promise for ophthalmology, but it remains unclear which training data source best conveys expert domain knowledge. Existing ophthalmic models are trained on fixed text templates, medical reports, or general biomedical literature, sources that have never been compared under matched conditions. To include domain-specific literature in this comparison, we present PubMed-Ophtha, a hierarchical dataset with high domain density of 102,023 panels with their subcaptions from 15,842 open-access articles in PubMed Central. We then finetuned identical CLIP models on each source, using a general biomedical literature model as baseline, and found that domain-specific literature achieved the best average performance across 110 clinical tasks, reaching a mean linear probing AUROC of 88.63% ahead of medical reports (85.68%). Restricting the dataset to fundus images, to the image count of the medical repo
arXiv:2603.23037v2 Announce Type: replace-cross Abstract: The trustworthy object detection capabilities of a novel Kolmogorov-Arnold network framework are examined here. The approach addresses a key limitation in computer vision for vehicle detection perception, and beyond. These systems offer limited transparency regarding the reliability of their confidence scores in visually degraded or ambiguous scenes. To this end, a Kolmogorov-Arnold network is employed as an interpretable post-hoc surrogate to model the trustworthiness of the You Only Look Once (Yolov10) detections using seven geometric and semantic features. The additive spline-based structure of the Kolmogorov-Arnold network enables direct visualisation of each feature's influence. This produces smooth and transparent functional mappings that reveal when the model's confidence is well supported and when it is unreliable. Furthermore, a bootstrapped language-image (BLIP) foundation model generates descriptive captions of each s
arXiv:2606.23989v4 Announce Type: replace Abstract: Large language models produce fluent multi-document summaries, but their attributions are typically coarse---whole documents or passages---and generated post hoc, leaving each statement hard to verify. We argue that attribution should be a structural property of generation rather than a downstream prediction. We present CAMS, a Claim-Anchored Multi-document Summarization framework that decomposes every source document into atomic claims whose provenance is resolved deterministically from verbatim quotes to token spans, clusters equivalent claims across documents while flagging inter-source conflicts, selects a support-aware and salient subset, and rewrites it so that every summary sentence terminates in claim identifiers resolving back to source spans. This yields a separation we make explicit: provenance is an invariant holding for every emitted sentence independently of model accuracy, whereas faithfulness is an objective that selec
arXiv:2606.19667v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding, but it also lengthens prompts and raises prefill cost. Prefix caching in serving engines such as vLLM reduces this cost only when requests share the same token prefix. In grounded generation, however, adjacent queries may retrieve overlapping evidence in different orders, so set overlap does not become reusable prefix overlap. We present CacheWeaver, a lightweight prompt-layer method for cache-aware evidence ordering. The method keeps a prefix tree over recently served evidence sequences and uses a greedy walk to place the most reusable prefix first, while leaving the serving engine and retrieved evidence set unchanged. Across three vLLM configurations, the method lowers median time-to-first-token (TTFT) by about 20-33 percent relative to retrieval-order prefix caching, without hurting answer quality in our QA tests. The greedy policy reaches 97.5 percent of the median T
arXiv:2606.12807v2 Announce Type: replace Abstract: Summaries of real-world events can become outdated as contexts evolve and new information arrives. A common response is to generate a new summary from the updated context, but full regeneration discards the previous draft, can obscure what changed, and may be unnecessary when only a few claims are unsupported. We study localized faithfulness repair: updating outdated spans in an existing summary while preserving supported content. We propose DETECT-REMASK-REPAIR, a diffusion-based framework that identifies, remasks, and repairs outdated regions with masked diffusion language models. To evaluate evolving-context summarization, we introduce StreamSum, a benchmark of synthetic event timelines. Experiments on DialogSum and StreamSum show that localized diffusion repair provides a controllable alternative to full rewriting: faithfulness-steered repair improves early drafts, one-step repair reduces repair cost to under half a second, with t
arXiv:2606.10403v3 Announce Type: replace Abstract: Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together they expose, across a wide range of VLMs (and LLMs with OCR), three patterns: (i) low-budget accuracy collapses on the high-human-error tail at every model size; (ii) test-time scaling (TTS) raises token use roughly linearly with cohort error rate, while accuracy gains follow a non-monotonic curve; (iii) within a single family, TTS flips between ant
arXiv:2606.07537v2 Announce Type: replace Abstract: Large language models produce fluent, confident, factually wrong output. Existing taxonomies classify these failures by output type -- intrinsic versus extrinsic, faithfulness versus factuality -- but say nothing about which computational component produced a given failure. We ask what would be required to attribute an individual hallucination to a specific component of the decoder-only stack. We treat three components -- self-attention's associative retrieval, the maximum-likelihood pretraining objective, and autoregressive commitment under exposure bias -- as candidate failure surfaces, justify their separability rather than assuming it, and specify an attribution procedure requiring only sampling access: an ordered set of three interventions on prefix, context, and frequency competition, together with a validation design based on independent annotation and a classifier baseline. We state five falsifiable predictions and identify co
arXiv:2605.25731v3 Announce Type: replace Abstract: Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we use enhanced prompts throughout training by incorporating original prompt texts and trait descriptions, providing richer semantic information for trait-specific score generation. Experiments across multiple backbone models show that our method consistently improves multi-trait scoring performance over supervised fine-tuning and scalar-reward optimization baselines, demonstrating the effective
arXiv:2605.15913v5 Announce Type: replace Abstract: Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained blocks, and the inefficiency of existing block fine-tuning methods that risk degrading performance. To address these, we first construct SemanticSeg, a large and diverse semantic segmentation dataset containing over 30k instances across 16 categories-including books, code, web text, and conversations with text lengths ranging from 2k to 32k. Using this dataset, we train a lightweight segmenter to automatically partition text into human-instinct-aligned blocks with controllable granularity. Second, we propose block distillation, a training framework that is more efficient than b
arXiv:2604.07035v3 Announce Type: replace Abstract: Open reasoning language models are often compared under mixed sample sizes, partially standardized prompts, and accuracy-centered summaries, which makes practical model selection difficult to interpret. We present a unified evaluation of seven open reasoning language model configurations across four benchmarks: ARC-Challenge, GSM8K, MATH levels 1 to 3, and TruthfulQA MC1. We test zero-shot, chain-of-thought (CoT), and few-shot CoT prompting on the same 238-example subset for every model--dataset--strategy condition, yielding a complete 7 x 4 x 3 design with 84 conditions and 19,992 evaluated examples. Beyond accuracy, we report Wilson confidence intervals, latency, peak video random access memory (VRAM), weighted aggregate performance, Pareto-efficient operating points, prompt-sensitivity metrics, and compatibility diagnostics. Gemma-4-26B-A4B with zero-shot prompting achieves the highest weighted score at 0.794. Gemma-4-E4B remains c
arXiv:2603.25183v2 Announce Type: replace Abstract: Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextual signals are unevenly beneficial across sentences. Existing training objectives do not explicitly model this variability, limiting a model's ability to adaptively exploit context. In this paper, we propose Cross-Preference Learning (CPL), a preference-based training framework that explicitly captures the complementary benefits of sentence-level and context-aware MT. CPL achieves this by integrating both intra- and cross-condition preferences into the preference optimization objective, providing explicit supervision to exploit informative context while remaining robust to uninformative context. We validate the proposed approach on several public context-aware MT tasks using multiple models, including Qwen3-4B, Qwen3-8B, and Llama-3-8B-Instruct. Experimental results demonstrate consistent i
arXiv:2603.21438v3 Announce Type: replace Abstract: To discover the weaknesses of LLMs, researchers often embed prompts into a vector space and cluster them to extract insightful patterns. However, vector embeddings primarily capture topical similarity; as a result, prompts that share a topic but differ in specificity, and consequently in difficulty, are often represented similarly, making fine-grained weakness analysis difficult. To address this limitation, we propose Prompt2Box, which embeds prompts into a box embedding space using a trained encoder. The encoder, trained on existing and synthesized datasets, outputs box embeddings that capture not only semantic similarity but also specificity relations between prompts (e.g., "writing an adventure story" is more specific than "writing a story"). We further develop a novel dimension reduction technique for box embeddings to facilitate dataset visualization and comparison. Our experiments demonstrate that box embeddings consistently cap
arXiv:2603.05617v2 Announce Type: replace Abstract: We present NotAI.AI, an explainable AI-generated text detection system. Instead of returning only a binary label or confidence score, the system shows which signals influenced the prediction and lets users inspect an attribution-based sensitivity estimate obtained by subtracting selected local contributions. NotAI.AI combines sentence-level conditional probability curvature, a neural detector score, and interpretable stylometric and readability features in an XGBoost meta-classifier. It explains predictions with TreeSHAP feature contributions and can turn the resulting evidence into a concise natural-language explanation. We evaluate the system on a category-balanced subset of RAID containing human-written, clean AI-generated, and attacked AI-generated texts. The full model outperforms variants based on individual feature families, reaching 0.9685 F1 on the held-out within-subset test split. In an automatic evaluation, two model judge
arXiv:2601.04202v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly applied to telecom engineering tasks, yet perform poorly on 3GPP specifications. These standards encode much of their technical information in complex tables, but LLM knowledge and interpretation of such tables remain largely unexplored. We introduce TeleTables, a benchmark comprising 2,220 tables from 13 3GPP specifications in four formats and 500 human-verified MCQs spanning direct retrieval to multi-step reasoning. Evaluating 20 open-weight LLMs across non reasoning, multimodal, reasoning, and table specialized architectures reveals two distinct performance bottlenecks. In the closed-book setting, domain knowledge is the primary constraint, with no general-purpose model exceeding 41% accuracy. When the table is provided as context, the best models exceed 90%, but performance degrades systematically with reasoning depth, evidence scope, and structural complexity, with a 32.2pp spread acr
arXiv:2509.22480v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this paper, we study a new perspective: the divergence in solutions generated by LLMs for a single problem. We show that higher solution divergence is positively related to better problem-solving abilities across various models. Based on this finding, we propose solution divergence as a novel metric that can support both SFT and RL strategies. We test this idea on three representative problem domains and find that using solution divergence consistently improves success rates. These results suggest that solution divergence is a simple but effective tool for advancing LLM training and evaluation.
arXiv:2509.21889v3 Announce Type: replace Abstract: Existing evaluations of foundation models predominantly focus on output correctness, treating interaction as a static exchange of information. However, such perspectives overlook the essence of the LLM-driven conversational experience, which is determined not only by content quality but, crucially, by dynamic service attributes such as generation velocity and latency patterns. To address this gap, we introduce QoNext, the first framework that adapts Quality of Experience (QoE) principles from networking and multimedia to the holistic assessment of human-AI interaction. QoNext identifies experiential factors that shape user experience and incorporates them into controlled experiments in simulated interaction scenarios, where human ratings are collected under diverse configurations. From these studies we construct the QoNext Database and train the QoNext Model, a neural predictor that estimates user experience directly from measurable s