arXiv:2510.22052v1 Announce Type: new Abstract: The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictate the prosperity and might of the world's economies. The AI market size is projected to grow from 189 billion USD in 2023 to 4.8 trillion USD by 2033. Currently, AI is dominated by large language models that exhibit linguistic and visual intelligence. However, training these models requires a massive amount of data scraped from the web as well as large amounts of energy (50--60 GWh to train GPT-4). Despite these costs, these models often hallucinate, a characteristic that prevents them from being deployed in critical application domains. In contrast, the human brain consumes only 20~W of power. What is needed is the next level of AI evolution in which lightweight domain-specific multimodal models with higher levels of intelligence can reason, plan, and make decisions in dynamic environments with real-time data and prior knowledge, while learning continuously and evolving in ways that enhance future decision-making capability. This will define the next wave of AI, progressing from today's large models, trained with vast amounts of data, to nimble energy-efficient domain-specific agents that can reason and think in a world full of uncertainty. To support such agents, hardware will need to be reimagined to allow energy efficiencies greater than 1000x over the state of the art. Such a vision of future AI systems is developed in this work.

arXiv:2510.22780v1 Announce Type: new Abstract: AI agents are continually optimized for tasks related to human work, such as software engineering and professional writing, signaling a pressing trend with significant impacts on the human workforce. However, these agent developments have often not been grounded in a clear understanding of how humans execute work, to reveal what expertise agents possess and the roles they can play in diverse workflows. In this work, we study how agents do human work by presenting the first direct comparison of human and agent workers across multiple essential work-related skills: data analysis, engineering, computation, writing, and design. To better understand and compare heterogeneous computer-use activities of workers, we introduce a scalable toolkit to induce interpretable, structured workflows from either human or agent computer-use activities. Using such induced workflows, we compare how humans and agents perform the same tasks and find that: (1) While agents exhibit promise in their alignment to human workflows, they take an overwhelmingly programmatic approach across all work domains, even for open-ended, visually dependent tasks like design, creating a contrast with the UI-centric methods typically used by humans. (2) Agents produce work of inferior quality, yet often mask their deficiencies via data fabrication and misuse of advanced tools. (3) Nonetheless, agents deliver results 88.3% faster and cost 90.4-96.2% less than humans, highlighting the potential for enabling efficient collaboration by delegating easily programmable tasks to agents.

arXiv:2510.23578v1 Announce Type: new Abstract: The rapid adoption of generative artificial intelligence (GenAI) technologies has led many organizations to integrate AI into their products and services, often without considering user preferences. Yet, public attitudes toward AI use, especially in impactful decision-making scenarios, are underexplored. Using a large-scale two-wave survey study (n_wave1=1514, n_wave2=1488) representative of the Swiss population, we examine shifts in public attitudes toward AI before and after the launch of ChatGPT. We find that the GenAI boom is significantly associated with reduced public acceptance of AI (see Figure 1) and increased demand for human oversight in various decision-making contexts. The proportion of respondents finding AI "not acceptable at all" increased from 23% to 30%, while support for human-only decision-making rose from 18% to 26%. These shifts have amplified existing social inequalities in terms of widened educational, linguistic, and gender gaps post-boom. Our findings challenge industry assumptions about public readiness for AI deployment and highlight the critical importance of aligning technological development with evolving public preferences.

arXiv:2510.21780v1 Announce Type: cross Abstract: In this study, we present an interpretable deep learning framework for the early detection of breast cancer using quantitative features extracted from digitized fine needle aspirate (FNA) images of breast masses. Our deep neural network, using ReLU activations, the Adam optimizer, and a binary cross-entropy loss, delivers state-of-the-art classification performance, achieving an accuracy of 0.992, precision of 1.000, recall of 0.977, and an F1 score of 0.988. These results substantially exceed the benchmarks reported in the literature. We evaluated the model under identical protocols against a suite of well-established algorithms (logistic regression, decision trees, random forests, stochastic gradient descent, K-nearest neighbors, and XGBoost) and found the deep model consistently superior on the same metrics. Recognizing that high predictive accuracy alone is insufficient for clinical adoption due to the black-box nature of deep learning models, we incorporated model-agnostic Explainable AI techniques such as SHAP and LIME to produce feature-level attributions and human-readable visualizations. These explanations quantify the contribution of each feature to individual predictions, support error analysis, and increase clinician trust, thus bridging the gap between performance and interpretability for real-world clinical use. The concave points feature of the cell nuclei is found to be the most influential feature positively impacting the classification task. This insight can be very helpful in improving the diagnosis and treatment of breast cancer by highlighting the key characteristics of breast tumor.

arXiv:2510.21810v1 Announce Type: cross Abstract: Diabetic Retinopathy (DR), a vision-threatening complication of Dia-betes Mellitus (DM), is a major global concern, particularly in India, which has one of the highest diabetic populations. Prolonged hyperglycemia damages reti-nal microvasculature, leading to DR symptoms like microaneurysms, hemor-rhages, and fluid leakage, which, if undetected, cause irreversible vision loss. Therefore, early screening is crucial as DR is asymptomatic in its initial stages. Fundus imaging aids precise diagnosis by detecting subtle retinal lesions. This paper introduces a hybrid diagnostic framework combining traditional feature extraction and deep learning (DL) to enhance DR detection. While handcrafted features capture key clinical markers, DL automates hierarchical pattern recog-nition, improving early diagnosis. The model synergizes interpretable clinical data with learned features, surpassing standalone DL approaches that demon-strate superior classification and reduce false negatives. This multimodal AI-driven approach enables scalable, accurate DR screening, crucial for diabetes-burdened regions.

arXiv:2510.21820v1 Announce Type: cross Abstract: The proliferation of high-dimensional datasets in fields such as genomics, healthcare, and finance has created an urgent need for machine learning models that are both highly accurate and inherently interpretable. While traditional deep learning approaches deliver strong predictive performance, their lack of transparency often impedes their deployment in critical, decision-sensitive applications. In this work, we introduce the Hierarchical Attention-based Interpretable Network (HAIN), a novel architecture that unifies multi-level attention mechanisms, dimensionality reduction, and explanation-driven loss functions to deliver interpretable and robust analysis of complex biomedical data. HAIN provides feature-level interpretability via gradientweighted attention and offers global model explanations through prototype-based representations. Comprehensive evaluation on The Cancer Genome Atlas (TCGA) dataset demonstrates that HAIN achieves a classification accuracy of 94.3%, surpassing conventional post-hoc interpretability approaches such as SHAP and LIME in both transparency and explanatory power. Furthermore, HAIN effectively identifies biologically relevant cancer biomarkers, supporting its utility for clinical and research applications. By harmonizing predictive accuracy with interpretability, HAIN advances the development of transparent AI solutions for precision medicine and regulatory compliance.

arXiv:2510.21823v1 Announce Type: cross Abstract: Deep Learning (DL) holds enormous potential for improving medical imaging diagnostics, yet the lack of interpretability in most models hampers clinical trust and adoption. This paper presents an explainable deep learning framework for detecting brain tumors in MRI scans and pneumonia in chest X-ray images using two leading Convolutional Neural Networks, ResNet50 and DenseNet121. These models were trained on publicly available Kaggle datasets comprising 7,023 brain MRI images and 5,863 chest X-ray images, achieving high classification performance. DenseNet121 consistently outperformed ResNet50 with 94.3 percent vs. 92.5 percent accuracy for brain tumors and 89.1 percent vs. 84.4 percent accuracy for pneumonia. For better explainability, Gradient-weighted Class Activation Mapping (Grad-CAM) was integrated to create heatmap visualizations superimposed on the test images, indicating the most influential image regions in the decision-making process. Interestingly, while both models produced accurate results, Grad-CAM showed that DenseNet121 consistently focused on core pathological regions, whereas ResNet50 sometimes scattered attention to peripheral or non-pathological areas. Combining deep learning and explainable AI offers a promising path toward reliable, interpretable, and clinically useful diagnostic tools.

arXiv:2510.21887v1 Announce Type: cross Abstract: In recent years, deep learning based generative models, particularly Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models (DMs), have been instrumental in in generating diverse, high-quality content across various domains, such as image and video synthesis. This capability has led to widespread adoption of these models and has captured strong public interest. As they continue to advance at a rapid pace, the growing volume of research, expanding application areas, and unresolved technical challenges make it increasingly difficult to stay current. To address this need, this survey introduces a comprehensive taxonomy that organizes the literature and provides a cohesive framework for understanding the development of GANs, VAEs, and DMs, including their many variants and combined approaches. We highlight key innovations that have improved the quality, diversity, and controllability of generated outputs, reflecting the expanding potential of generative artificial intelligence. In addition to summarizing technical progress, we examine rising ethical concerns, including the risks of misuse and the broader societal impact of synthetic media. Finally, we outline persistent challenges and propose future research directions, offering a structured and forward looking perspective for researchers in this fast evolving field.

arXiv:2510.22056v1 Announce Type: cross Abstract: Anomaly detection in surveillance videos remains a challenging task due to the diversity of abnormal events, class imbalance, and scene-dependent visual clutter. To address these issues, we propose a robust deep learning framework that integrates human-centric preprocessing with spatio-temporal modeling for multi-class anomaly classification. Our pipeline begins by applying YOLO-World - an open-vocabulary vision-language detector - to identify human instances in raw video clips, followed by ByteTrack for consistent identity-aware tracking. Background regions outside detected bounding boxes are suppressed via Gaussian blurring, effectively reducing scene-specific distractions and focusing the model on behaviorally relevant foreground content. The refined frames are then processed by an ImageNet-pretrained InceptionV3 network for spatial feature extraction, and temporal dynamics are captured using a bidirectional LSTM (BiLSTM) for sequence-level classification. Evaluated on a five-class subset of the UCF-Crime dataset (Normal, Burglary, Fighting, Arson, Explosion), our method achieves a mean test accuracy of 92.41% across three independent trials, with per-class F1-scores consistently exceeding 0.85. Comprehensive evaluation metrics - including confusion matrices, ROC curves, and macro/weighted averages - demonstrate strong generalization and resilience to class imbalance. The results confirm that foreground-focused preprocessing significantly enhances anomaly discrimination in real-world surveillance scenarios.

arXiv:2510.22206v1 Announce Type: cross Abstract: Execution algorithms are vital to modern trading, they enable market participants to execute large orders while minimising market impact and transaction costs. As these algorithms grow more sophisticated, optimising them becomes increasingly challenging. In this work, we present a reinforcement learning (RL) framework for discovering optimal execution strategies, evaluated within a reactive agent-based market simulator. This simulator creates reactive order flow and allows us to decompose slippage into its constituent components: market impact and execution risk. We assess the RL agent's performance using the efficient frontier based on work by Almgren and Chriss, measuring its ability to balance risk and cost. Results show that the RL-derived strategies consistently outperform baselines and operate near the efficient frontier, demonstrating a strong ability to optimise for risk and impact. These findings highlight the potential of reinforcement learning as a powerful tool in the trader's toolkit.

arXiv:2510.22242v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly serve as research assistants, yet their reliability in scholarly tasks remains under-evaluated. In this work, we introduce PaperAsk, a benchmark that systematically evaluates LLMs across four key research tasks: citation retrieval, content extraction, paper discovery, and claim verification. We evaluate GPT-4o, GPT-5, and Gemini-2.5-Flash under realistic usage conditions-via web interfaces where search operations are opaque to the user. Through controlled experiments, we find consistent reliability failures: citation retrieval fails in 48-98% of multi-reference queries, section-specific content extraction fails in 72-91% of cases, and topical paper discovery yields F1 scores below 0.32, missing over 60% of relevant literature. Further human analysis attributes these failures to the uncontrolled expansion of retrieved context and the tendency of LLMs to prioritize semantically relevant text over task instructions. Across basic tasks, the LLMs display distinct failure behaviors: ChatGPT often withholds responses rather than risk errors, whereas Gemini produces fluent but fabricated answers. To address these issues, we develop lightweight reliability classifiers trained on PaperAsk data to identify unreliable outputs. PaperAsk provides a reproducible and diagnostic framework for advancing the reliability evaluation of LLM-based scholarly assistance systems.

arXiv:2510.22500v1 Announce Type: cross Abstract: As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on tasks that require deep knowledge and skills of multiple domains. Unfortunately, even the best human experts are knowledgeable only in a single narrow area, and will not be able to evaluate the correctness of advanced AI systems on such superhuman tasks. However, based on their narrow expertise, humans may provide a weak signal, i.e., a complementary label indicating an option that is incorrect. For example, a cardiologist could state that "this is not related to cardiology,'' even if they cannot identify the true disease. Based on this weak signal, we propose a scalable oversight framework that enables us to evaluate frontier AI systems without the need to prepare the ground truth. We derive an unbiased estimator of top-1 accuracy from complementary labels and quantify how many complementary labels are needed to match the variance of ordinary labels. We further introduce two estimators to combine scarce ordinary labels with abundant complementary labels. We provide finite-sample deviation guarantees for both complementary-only and the mixed estimators. Empirically, we show that we can evaluate the output of large language models without the ground truth, if we have complementary labels. We further show that we can train an AI system with such weak signals: we show how we can design an agentic AI system automatically that can perform better with this partitioned human supervision. Our code is available at https://github.com/R-Yin-217/Scalable-Oversight-via-Human-Partitioned-Supervision.

arXiv:2510.22620v1 Announce Type: cross Abstract: AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional software with AI components entangles novel LLM vulnerabilities with conventional security risks. Existing frameworks only partially address these challenges as they either capture specific vulnerabilities only or require modeling of complete agents. To address these limitations, we introduce threat snapshots: a framework that isolates specific states in an agent's execution flow where LLM vulnerabilities manifest, enabling the systematic identification and categorization of security risks that propagate from the LLM to the agent level. We apply this framework to construct the $\operatorname{b}^3$ benchmark, a security benchmark based on 194331 unique crowdsourced adversarial attacks. We then evaluate 31 popular LLMs with it, revealing, among other insights, that enhanced reasoning capabilities improve security, while model size does not correlate with security. We release our benchmark, dataset, and evaluation code to facilitate widespread adoption by LLM providers and practitioners, offering guidance for agent developers and incentivizing model developers to prioritize backbone security improvements.

arXiv:2510.22628v1 Announce Type: cross Abstract: This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with FAISS-indexed SBERT embedding representations that capture the semantic meaning of prompts, combined with fine-tuned transformer classifiers, which are machine learning models specialized for distinguishing between benign and adversarial language inputs. It identifies adversarial prompts in both direct and obfuscated attack vectors. A core innovation is the classifier-retriever fusion module, which dynamically computes context-aware risk scores that estimate how likely a prompt is to be adversarial based on its content and context. The framework ensures multilingual resilience with a language-agnostic preprocessing layer. This component automatically translates non-English prompts into English for semantic evaluation, enabling consistent detection across over 100 languages. The system includes a HITL feedback loop, where decisions made by the automated system are reviewed by human experts for continual learning and rapid adaptation under adversarial pressure. Sentra-Guard maintains an evolving dual-labeled knowledge base of benign and malicious prompts, enhancing detection reliability and reducing false positives. Evaluation results show a 99.96% detection rate (AUC = 1.00, F1 = 1.00) and an attack success rate (ASR) of only 0.004%. This outperforms leading baselines such as LlamaGuard-2 (1.3%) and OpenAI Moderation (3.7%). Unlike black-box approaches, Sentra-Guard is transparent, fine-tunable, and compatible with diverse LLM backends. Its modular design supports scalable deployment in both commercial and open-source environments. The system establishes a new state-of-the-art in adversarial LLM defense.

arXiv:2510.23379v1 Announce Type: cross Abstract: We investigate a relatively underexplored class of hybrid neurosymbolic models integrating symbolic learning with neural reasoning to construct data generators meeting formal correctness criteria. In \textit{Symbolic Neural Generators} (SNGs), symbolic learners examine logical specifications of feasible data from a small set of instances -- sometimes just one. Each specification in turn constrains the conditional information supplied to a neural-based generator, which rejects any instance violating the symbolic specification. Like other neurosymbolic approaches, SNG exploits the complementary strengths of symbolic and neural methods. The outcome of an SNG is a triple $(H, X, W)$, where $H$ is a symbolic description of feasible instances constructed from data, $X$ a set of generated new instances that satisfy the description, and $W$ an associated weight. We introduce a semantics for such systems, based on the construction of appropriate \textit{base} and \textit{fibre} partially-ordered sets combined into an overall partial order, and outline a probabilistic extension relevant to practical applications. In this extension, SNGs result from searching over a weighted partial ordering. We implement an SNG combining a restricted form of Inductive Logic Programming (ILP) with a large language model (LLM) and evaluate it on early-stage drug design. Our main interest is the description and the set of potential inhibitor molecules generated by the SNG. On benchmark problems -- where drug targets are well understood -- SNG performance is statistically comparable to state-of-the-art methods. On exploratory problems with poorly understood targets, generated molecules exhibit binding affinities on par with leading clinical candidates. Experts further find the symbolic specifications useful as preliminary filters, with several generated molecules identified as viable for synthesis and wet-lab testing.

arXiv:2508.02630v2 Announce Type: replace Abstract: Online marketplaces will be transformed by autonomous AI agents acting on behalf of consumers. Rather than humans browsing and clicking, AI agents can parse webpages or interact through APIs to evaluate products, and transact. This raises a fundamental question: what do AI agents buy-and why? We develop ACES, a sandbox environment that pairs a platform-agnostic agent with a fully programmable mock marketplace to study this. We first explore aggregate choices, revealing that modal choices can differ across models, with AI agents sometimes concentrating on a few products, raising competition questions. We then analyze the drivers of choices through rationality checks and randomized experiments on product positions and listing attributes. Models show sizeable and heterogeneous position effects: all favor the top row, yet different models prefer different columns, undermining the assumption of a universal ``top'' rank. They penalize sponsored tags, reward endorsements, and sensitivities to price, ratings, and reviews are directionally as expected, but vary sharply across models. Finally, we find that a seller-side agent that makes minor tweaks to product descriptions can deliver substantial market-share gains by targeting AI buyer preferences. Our findings reveal how AI agents behave in e-commerce, and surface concrete seller strategy, platform design, and regulatory questions.

arXiv:2509.05818v2 Announce Type: replace Abstract: Patients must possess the knowledge necessary to actively participate in their care. We present NoteAid-Chatbot, a conversational AI that promotes patient understanding via a novel 'learning as conversation' framework, built on a multi-agent large language model (LLM) and reinforcement learning (RL) setup without human-labeled data. NoteAid-Chatbot was built on a lightweight LLaMA 3.2 3B model trained in two stages: initial supervised fine-tuning on conversational data synthetically generated using medical conversation strategies, followed by RL with rewards derived from patient understanding assessments in simulated hospital discharge scenarios. Our evaluation, which includes comprehensive human-aligned assessments and case studies, demonstrates that NoteAid-Chatbot exhibits key emergent behaviors critical for patient education, such as clarity, relevance, and structured dialogue, even though it received no explicit supervision for these attributes. Our results show that even simple Proximal Policy Optimization (PPO)-based reward modeling can successfully train lightweight, domain-specific chatbots to handle multi-turn interactions, incorporate diverse educational strategies, and meet nuanced communication objectives. Our Turing test demonstrates that NoteAid-Chatbot surpasses non-expert human. Although our current focus is on healthcare, the framework we present illustrates the feasibility and promise of applying low-cost, PPO-based RL to realistic, open-ended conversational domains, broadening the applicability of RL-based alignment methods.

arXiv:2406.11477v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown remarkable capabilities in many languages beyond English. Yet, LLMs require more inference steps when generating non-English text due to their reliance on English-centric tokenizers and vocabulary, resulting in higher usage costs to non-English speakers. Vocabulary expansion with target language tokens is a widely used cross-lingual vocabulary adaptation approach to remedy this issue. Despite its effectiveness in inference speedup, previous work on vocabulary expansion has focused on high-resource settings assuming access to a substantial amount of target language data to effectively initialize the embeddings of the new tokens and adapt the LLM to the target language. However, vocabulary expansion in low-resource settings has yet to be explored. In this article, we investigate vocabulary expansion in low-resource settings by considering embedding initialization methods and continual pre-training strategies. Through extensive experiments across typologically diverse languages, tasks and models, we establish a set of strategies to perform vocabulary expansion for faster inference, while striving to maintain competitive downstream performance to baselines. This is achieved with only 30K sentences ($\sim$0.01GB text data) from the target language.

arXiv:2505.17895v2 Announce Type: replace-cross Abstract: The quality of foundation models depends heavily on their training data. Consequently, great efforts have been put into dataset curation. Yet most approaches rely on manual tuning of coarse-grained mixtures of large buckets of data, or filtering by hand-crafted heuristics. An approach that is ultimately more scalable (let alone more satisfying) is to \emph{learn} which data is actually valuable for training. This type of meta-learning could allow more sophisticated, fine-grained, and effective curation. Our proposed \emph{DataRater} is an instance of this idea. It estimates the value of training on any particular data point. This is done by meta-learning using `meta-gradients', with the objective of improving training efficiency on held out data. In extensive experiments across a range of model scales and datasets, we find that using our DataRater to filter data is highly effective, resulting in significantly improved compute efficiency.

arXiv:2506.05596v2 Announce Type: replace-cross Abstract: Inverse folding models have proven to be highly effective zero-shot predictors of protein stability. Despite this success, the link between the amino acid preferences of an inverse folding model and the free-energy considerations underlying thermodynamic stability remains incompletely understood. A better understanding would be of interest not only from a theoretical perspective, but also potentially provide the basis for stronger zero-shot stability prediction. In this paper, we take steps to clarify the free-energy foundations of inverse folding models. Our derivation reveals the standard practice of likelihood ratios as a simplistic approximation and suggests several paths towards better estimates of the relative stability. We empirically assess these approaches and demonstrate that considerable gains in zero-shot performance can be achieved with fairly simple means.