{
    "ok": true,
    "version": "3.0.0-mission-control",
    "checkedAt": "2026-10-28T18:55:10+00:00",
    "elapsedMs": 86,
    "count": 20,
    "categories": {
        "ai": 20
    },
    "items": [
        {
            "id": "735f82c27e115ab5168bc3848f2bd2c1c0986bb8",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Counting the Bandages: On measuring the time that AI saves",
            "summary": "arXiv:2610.35942v1 Announce Type: new Abstract: I consider what it means for AI assistance to save time. I contrast a stopwatch view, on which time saved is whatever the clock records, with a ledger view, on which it is a counterfactual that has to be read next to the errors the work lets through, and I argue for the latter. The argument has four parts. I define a model-free pair of quantities, time saved and excess escaped defects, and one decision number built from them: the break-even defect cost. I give a baseline model of checking in which, until the model is good enough not to check, a calibrated worker's escaped-defect rate does not depend on how good the model is; checking time grows with the logarithm of the model's error rate; and over-trust buys minutes on the clock at a larger cost in total minutes. I show what randomized studies can and cannot identify, and I replicate METR…",
            "url": "https://arxiv.org/abs/2610.35942",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Counting the Bandages: On measuring the time that AI saves",
                "summary": "arXiv:2610.35942v1 Announce Type: new \nAbstract: I consider what it means for AI assistance to save time. I contrast a stopwatch view, on which time saved is whatever the clock records, with a ledger view, on which it is a counterfactual that has to be read next to the errors the work lets through, and I argue for the latter. The argument has four parts. I define a model-free pair of quantities, time saved and excess escaped defects, and one decision number built from them: the break-even defect cost. I give a baseline model of checking in which, until the model is good enough not to check, a calibrated worker's escaped-defect rate does not depend on how good the model is; checking time grows with the logarithm of the model's error rate; and over-trust buys minutes on the clock at a larger cost in total minutes. I show what randomized studies can and cannot identify, and I replicate METR's developer study from its public data: the same 246 issues support a slowdown of 19% or 24% depending on the estimand (34% without adjusting for a chance imbalance), and AI helped on somewhere between 3% and 82% of them. Finally, I restate the published record, with stated bounds in place of imported point assumptions. In GDPval's own review-every-output workflow, review time alone caps GPT-5's speedup at 3.6x; the consultants outside the frontier were faster, and more often wrong. Last, I test two of the model's predictions in a small pre-specified experiment on AI reviewers checking AI drafts of the same kind of brief, built from SEC filings made after the models' training data were collected. Told the drafter's true error rate, the reviewer checked more as it rose, but all-or-nothing, switching near where its prompt's costs break even. Told that the drafter erred ten times less often than it did, it checked 7 fewer of 9 figures and let a wrong figure through in 22.5% of briefs instead of none: faster and worse, entirely through reduced effort.",
                "url": "https://arxiv.org/abs/2610.35942",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "577b5330c47047cdfbff35fd2b5da8c6c1e2f40b",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases",
            "summary": "arXiv:2610.35984v1 Announce Type: new Abstract: Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generation using Deep Convolu tional Generative Adversarial Networks (DCGANs), to create new data samples. Second, we exploit this generated data in three scenarios: (S1) balancing class distribution in the original dataset, (S2) increasing the number of samples per class, and (S3) expanding the dataset while maintaining balanced classes. Third, we evaluate the impact of these data distributions (S1, S2,…",
            "url": "https://arxiv.org/abs/2610.35984",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases",
                "summary": "arXiv:2610.35984v1 Announce Type: new \nAbstract: Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generation using Deep Convolu tional Generative Adversarial Networks (DCGANs), to create new data samples. Second, we exploit this generated data in three scenarios: (S1) balancing class distribution in the original dataset, (S2) increasing the number of samples per class, and (S3) expanding the dataset while maintaining balanced classes. Third, we evaluate the impact of these data distributions (S1, S2, S3) on model perfor mance using the EfficientNetV2B0 architecture with pre-trained and fine-tuned weights. The experimental results show a substantial improvement in classifica tion accuracy, emphasizing the critical role of data diversity and class balance. These findings highlight the effectiveness and adaptability of the proposed strat egy of data generation and distribution for enhancing dataset quality, offering promising applications in plant disease detection and precision agriculture.",
                "url": "https://arxiv.org/abs/2610.35984",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "d9783dac366590b9b1bcd4ee7cccbb2962a3dd8a",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents",
            "summary": "arXiv:2610.36077v1 Announce Type: new Abstract: Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Cap…",
            "url": "https://arxiv.org/abs/2610.36077",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents",
                "summary": "arXiv:2610.36077v1 Announce Type: new \nAbstract: Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.",
                "url": "https://arxiv.org/abs/2610.36077",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "97374c790247917b80a1b2000b056ac4c2a48fe8",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction",
            "summary": "arXiv:2610.36100v1 Announce Type: new Abstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion an…",
            "url": "https://arxiv.org/abs/2610.36100",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction",
                "summary": "arXiv:2610.36100v1 Announce Type: new \nAbstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation over MIMIC, all 13 cohort states execute successfully, while correction trajectories demonstrate selective preservation of unaffected computations and recomputation of changed or dependent nodes. Together, these results show that localized semantic steering can substantially reduce correction latency and model calls while maintaining strong requirement-level accuracy.",
                "url": "https://arxiv.org/abs/2610.36100",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "4a3e19bca2fb479d6dcdf96ab780557ca160b004",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction",
            "summary": "arXiv:2610.36116v1 Announce Type: new Abstract: As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \\emph{why} should humans keep doing science, and \\emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first. It holds that one indispensable aim of science is \\emph{durable, collective human understanding of the world, pursued in service of human ends and values}. From this principle it derives a two-part test for when a research task can be delegated to AI. The first part, \\emph{human understanding}, requires that the scientific community remain able to explain, defend and contest the resulting claims, and retain the skills to do so. The second, \\emph{human direction}, requires that judgments about which questions matter and what findings mean stay with accountable humans…",
            "url": "https://arxiv.org/abs/2610.36116",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction",
                "summary": "arXiv:2610.36116v1 Announce Type: new \nAbstract: As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \\emph{why} should humans keep doing science, and \\emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first. It holds that one indispensable aim of science is \\emph{durable, collective human understanding of the world, pursued in service of human ends and values}. From this principle it derives a two-part test for when a research task can be delegated to AI. The first part, \\emph{human understanding}, requires that the scientific community remain able to explain, defend and contest the resulting claims, and retain the skills to do so. The second, \\emph{human direction}, requires that judgments about which questions matter and what findings mean stay with accountable humans. Applying the test to each phase of research in the Contributor Roles Taxonomy (CRediT) yields recommendations that fields can tailor to their questions and methods. The framework differs from existing guidance in three ways. It rests on an account of what science is for rather than on integrity norms. It holds even if AI outperforms human researchers, rather than depending on AI's current limitations. And it judges each use of AI by its effects on human understanding and direction rather than by the type of tool, across every phase of research, including peer review and the training of new researchers. It closes with the reforms needed to keep science aimed at human understanding and direction.",
                "url": "https://arxiv.org/abs/2610.36116",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "e51210b1fe51556b6bb9057c20dc02a9479e9e9d",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors",
            "summary": "arXiv:2610.36146v1 Announce Type: new Abstract: Prompt optimization should improve the image a user receives without changing the scene the user requested. Yet stylistic rewriting can weaken object attributes and relations even when global text--image similarity remains high. We propose StruPO, a structure-aware prompt editor that uses a calibrated scene graph as a shared representation for policy conditioning and image-grounded supervision. The graph exposes what should be preserved, while deletion, reordering, and insertion provide a token-aligned way to modify the prompt. This turns structural feedback from an external critique into a training signal for a reusable editing policy. Learning from that signal requires handling both uncertain grounding and stochastic image generation. StruPO retains grounding confidence through smooth reward shaping and averages multiple images for each …",
            "url": "https://arxiv.org/abs/2610.36146",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors",
                "summary": "arXiv:2610.36146v1 Announce Type: new \nAbstract: Prompt optimization should improve the image a user receives without changing the scene the user requested. Yet stylistic rewriting can weaken object attributes and relations even when global text--image similarity remains high. We propose StruPO, a structure-aware prompt editor that uses a calibrated scene graph as a shared representation for policy conditioning and image-grounded supervision. The graph exposes what should be preserved, while deletion, reordering, and insertion provide a token-aligned way to modify the prompt. This turns structural feedback from an external critique into a training signal for a reusable editing policy. Learning from that signal requires handling both uncertain grounding and stochastic image generation. StruPO retains grounding confidence through smooth reward shaping and averages multiple images for each edit before computing group-relative advantages. Experiments span three disjoint 2K-prompt test sets and four frozen generation backbones, with comparisons to learned prompt optimizers, iterative structural feedback, diffusion-model fine-tuning, and inference-time attention control. StruPO improves the faithfulness--aesthetics trade-off, with consistent gains in relational fidelity. Independent automatic evaluators and a 15-annotator study provide complementary evidence, and human preference margins increase with relation complexity. Controlled ablations connect these gains to graph conditioning, local editing, and image-grounded learning. The resulting policy produces reusable optimized text in one pass after graph calibration, without an iterative critique--rewrite loop.",
                "url": "https://arxiv.org/abs/2610.36146",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "bd35698e9fe7f1bb1e66e80894f51613c341adfa",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Don't Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule",
            "summary": "arXiv:2610.36169v1 Announce Type: new Abstract: A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model's memory. Each rule is confidently wrong in some deployment. In a decision-theoretic model of two sources, the score of any fixed rule is linear in the share of reliable contexts while the best attainable score is convex, so every fixed rule is beaten wherever it is not exactly optimal; and a symmetric divergence between the two sources, the signal adaptive decoding uses, carries no information about which one is right. Resolving a conflict therefore needs two inputs that no existing method keeps: evid…",
            "url": "https://arxiv.org/abs/2610.36169",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Don't Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule",
                "summary": "arXiv:2610.36169v1 Announce Type: new \nAbstract: A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model's memory. Each rule is confidently wrong in some deployment. In a decision-theoretic model of two sources, the score of any fixed rule is linear in the share of reliable contexts while the best attainable score is convex, so every fixed rule is beaten wherever it is not exactly optimal; and a symmetric divergence between the two sources, the signal adaptive decoding uses, carries no information about which one is right. Resolving a conflict therefore needs two inputs that no existing method keeps: evidence about each source separately, and a prior on how often the context is right. We test these claims on GRACE, a benchmark that intervenes on the knowledge-graph context of a fixed question, so that what the model knows, what the context says and what is true are measured separately. There, every baseline from four families is strong on right contexts or on wrong ones, never on both. We then build the two inputs: the model states its knowledge as notes, a small policy voices each note with a calibrated confidence, a reader answers in two voices, and a selector commits or abstains under a prior $\\pi$ applied as an exact prior shift. With $\\pi$ set to the true share of right contexts, the system is above the best baseline at every mixture of GRACE contexts, by up to 26 points. Its overall score is 45.3 and 35.0 (Qwen3.5-35B-A3B, Llama-3.1-8B), against 29.4 and 27.5 for the best baseline. On preregistered ClashEval it beats same-backbone CK-PLUG and TCR by 12 and 26 points. Where the model lacks the knowledge, the gains vanish, as the theory predicts.",
                "url": "https://arxiv.org/abs/2610.36169",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "4210209ec892e20d03f8c1c99e0dff1122bd3723",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data",
            "summary": "arXiv:2610.36183v1 Announce Type: new Abstract: We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times. Rather than modeling space ownership through position density estimation or closed-form physics-based models, we cast TTA as a conditional quantile regression problem, estimating the lower quantile of locomotion time so the model learns a player's lower-envelope arrival time. We train the model on optical tracking data from all 64 matches of the PFF FC FIFA World Cup 2022 dataset, and evaluate a lightweight multilayer perceptron against six player-motion models from the literature, re-expressed as TTA predictors, and a learned reachable- hull baseline. Across our evaluation metrics, the MLP consistently outperforms …",
            "url": "https://arxiv.org/abs/2610.36183",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data",
                "summary": "arXiv:2610.36183v1 Announce Type: new \nAbstract: We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times. Rather than modeling space ownership through position density estimation or closed-form physics-based models, we cast TTA as a conditional quantile regression problem, estimating the lower quantile of locomotion time so the model learns a player's lower-envelope arrival time. We train the model on optical tracking data from all 64 matches of the PFF FC FIFA World Cup 2022 dataset, and evaluate a lightweight multilayer perceptron against six player-motion models from the literature, re-expressed as TTA predictors, and a learned reachable- hull baseline. Across our evaluation metrics, the MLP consistently outperforms every physics-based baseline. To probe the generality of the learned locomotion model, we further evaluate it on basketball tracking data and a single-game NFL tracking dataset, analyzing the transferability of player motion dynamics across sports. Our project is available at https://github.com/mguti97/TTA-Quantile.",
                "url": "https://arxiv.org/abs/2610.36183",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "e868fa3fb83720f1754cf4b5e89554e31d273f1d",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Skill Dreaming: Evolving Repository Skills through Pull Request Streams",
            "summary": "arXiv:2610.36188v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolutio…",
            "url": "https://arxiv.org/abs/2610.36188",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Skill Dreaming: Evolving Repository Skills through Pull Request Streams",
                "summary": "arXiv:2610.36188v1 Announce Type: new \nAbstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolution. To enable this co-evolution of PRs, repositories, and skills, we propose Skill Dreaming, a framework that learns from PR streams to guide continuous repository development and maintenance. Given a repository and its PR history, Skill Dreaming builds a repository-specific skill library by extracting executable knowledge from validated PRs and continuously refines the skills as new PR information becomes available. These skills guide coding agents not only in implementing requested features but also in maintaining associated tests, documentation, compatibility, and repository conventions. By integrating PR analysis, skill management, code execution, and continuous integration, Skill Dreaming provides an end-to-end workflow for applying learned skills to repository changes and incorporating subsequent PR outcomes into future skill updates.",
                "url": "https://arxiv.org/abs/2610.36188",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "45cf85af86c821b3ecbda8bca384b287a767d69a",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge",
            "summary": "arXiv:2610.36234v1 Announce Type: new Abstract: Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes. Although large language models (LLMs) are promising for requirement quality assessment, prior work shows that off-the-shelf models miss a large share of expert-identified defects, perform unevenly across quality criteria, and vary across executions. This study investigates whether infusing expert-derived SE knowledge can improve LLM-based requirement quality evaluation beyond off-the-shelf capability. We present MARQ, a modular, LLM-agnostic prototype that supplements LLMs with a criterion-specific knowledge stack operationalizing INCOSE requirement quality criteria and evaluated against off-the-shelf baselines on an expert-labeled NASA requirement set using Claude Opus 5, GPT…",
            "url": "https://arxiv.org/abs/2610.36234",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge",
                "summary": "arXiv:2610.36234v1 Announce Type: new \nAbstract: Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes. Although large language models (LLMs) are promising for requirement quality assessment, prior work shows that off-the-shelf models miss a large share of expert-identified defects, perform unevenly across quality criteria, and vary across executions. This study investigates whether infusing expert-derived SE knowledge can improve LLM-based requirement quality evaluation beyond off-the-shelf capability. We present MARQ, a modular, LLM-agnostic prototype that supplements LLMs with a criterion-specific knowledge stack operationalizing INCOSE requirement quality criteria and evaluated against off-the-shelf baselines on an expert-labeled NASA requirement set using Claude Opus 5, GPT-5.6 Sol, and the open-weight Gemma 3 12B, with 100 executions per model. MARQ achieves median F1 scores of 0.80 for Claude Opus 5, 0.62 for GPT-5.6 Sol, and 0.53 for Gemma 3 12B, compared with off-the-shelf baselines of 0.55, 0.52, and 0.18, respectively. However, the nature of these gains is model-dependent. Claude Opus 5 improves defect detection and false-alarm control; GPT-5.6 Sol gains detection and better execution-level consistency at the cost of more false alarms; and Gemma 3 12B reaches the performance of off-the-shelf proprietary models, although it remains highly variable. Criterion-level analysis shows gains concentrated in Correctness and Conformance, trade-offs between misses and false alarms within individual criteria, and model-dependent responses across several criteria. These findings position SE knowledge infusion as a promising model-agnostic pathway for strengthening trustworthy LLM-based RE support while underscoring the need for criterion-specific interventions and human-in-the-loop review.",
                "url": "https://arxiv.org/abs/2610.36234",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "712deab9d43fc113bdcc6031c7e6781647bbb3fa",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals",
            "summary": "arXiv:2610.36239v1 Announce Type: new Abstract: Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term history and community signals is universally beneficial, we study when it actually helps. We propose BehaveRec, a three-signal framework combining a causal session transformer, a bidirectional User History Encoder over a 90-day window, and a GraphSAGE module over a user-user graph built from behavioral embedding similarity rather than item co-occurrence; a learned gate blends the three signals per user. On an industrial dataset of 137M sequences from 12.6M users, BehaveRec improves R@5 by +3.2% over SASRec, with a larger-capacity SASRec baseline (more parameters than BehaveRec) still trailing by +2.5%, ruling …",
            "url": "https://arxiv.org/abs/2610.36239",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals",
                "summary": "arXiv:2610.36239v1 Announce Type: new \nAbstract: Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term history and community signals is universally beneficial, we study when it actually helps. We propose BehaveRec, a three-signal framework combining a causal session transformer, a bidirectional User History Encoder over a 90-day window, and a GraphSAGE module over a user-user graph built from behavioral embedding similarity rather than item co-occurrence; a learned gate blends the three signals per user. On an industrial dataset of 137M sequences from 12.6M users, BehaveRec improves R@5 by +3.2% over SASRec, with a larger-capacity SASRec baseline (more parameters than BehaveRec) still trailing by +2.5%, ruling out capacity as the explanation. More importantly, a user-level stratification by history length reveals a clear dose-response relationship: BehaveRec's advantage is negligible below roughly 10 interactions and grows monotonically with history richness, reaching +0.017 R@5 for users with 101+ events. This pattern is corroborated across one industrial and three public datasets spanning history-rich to history-sparse regimes, where session-only models remain preferable. These headline results, and the resulting deployment threshold, are established for category-level intent prediction; a preliminary, single-run check on the full item-level vocabulary yields a directionally mixed result and is scoped as an open question rather than a claim. We use these results to derive a practical deployment rule -- roughly 20 interactions per user -- for when long-term history and behavioral-graph signals are worth their added complexity. Despite this added complexity, BehaveRec remains lightweight: it uses 5.67M parameters and trains on a single GPU in under two days.",
                "url": "https://arxiv.org/abs/2610.36239",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "450ecff2f12d955f1af86f29dbda5d3a42ece828",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "A Smart Instant Book Filter Model based on Dual-Objective Optimization",
            "summary": "arXiv:2610.36287v1 Announce Type: new Abstract: Hospitality service in online marketplaces has become increasingly popular over the past few years, not only because it helps people easily rent short-term lodging but also because it empowers travelers to connect with locals and feel belonging. A typical pattern of these industries is a central platform mediating the economic interactions between guests and hosts, where a successful booking experience is the key to user satisfaction. However, one of the biggest challenges is the possible delay of response and chance of rejection when guests try to book a request-to-book listing. Previously, we enabled the instant book feature to allow hosts to instantly accept qualified guests and guests to confirm bookings immediately. Yet the symptom has not been alleviated given mixed request-to-book and instant book listing supply in search results. O…",
            "url": "https://arxiv.org/abs/2610.36287",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "A Smart Instant Book Filter Model based on Dual-Objective Optimization",
                "summary": "arXiv:2610.36287v1 Announce Type: new \nAbstract: Hospitality service in online marketplaces has become increasingly popular over the past few years, not only because it helps people easily rent short-term lodging but also because it empowers travelers to connect with locals and feel belonging. A typical pattern of these industries is a central platform mediating the economic interactions between guests and hosts, where a successful booking experience is the key to user satisfaction. However, one of the biggest challenges is the possible delay of response and chance of rejection when guests try to book a request-to-book listing. Previously, we enabled the instant book feature to allow hosts to instantly accept qualified guests and guests to confirm bookings immediately. Yet the symptom has not been alleviated given mixed request-to-book and instant book listing supply in search results. One possible solution is to promote all instant book listings in search results; however, booking rate will be damaged due to some improperly promoted low quality listings.\n  In this paper, we present a novel smart instant book filter system that applies the instant book filter intelligently and shifts request-to-book to instant book without hurting booking rate. Compared with traditional two-sided markets research that targets finding strategies to maximize a single overall social welfare goal, our proposed system aims to maximize the instant book rate with the constraint that booking rate should not decrease, forming a dual-objective optimization problem.\n  We show A/B testing results for our system exposed to global users, demonstrating that our model performs better than previous human-expert-tuned models in terms of both instant book rate and overall booking rate. We also achieved improved metrics such as the host instant book adoption rate. The proposed system has been deployed to production and is serving millions of users every day.",
                "url": "https://arxiv.org/abs/2610.36287",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "449db2adf3d062810ee59491eb8d22d6492fd646",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks",
            "summary": "arXiv:2610.36298v1 Announce Type: new Abstract: Machine learning models deployed behind query interfaces expose more than their predictions, because an adversary can use those predictions to rebuild the model itself. Model stealing attacks (MSAs) exploit this exposure by training a surrogate model that replicates the decision behavior of a target through black-box queries alone, without access to its parameters or training data. These attacks are well characterized for conventional artificial neural networks (ANNs), yet spiking neural networks (SNNs) process information in a fundamentally different way. SNNs communicate through sparse, discrete spikes, and their outputs depend on membrane potentials that evolve over time rather than on a static mapping from input to output. This temporal mode of computation suggests that the decision behavior of an SNN may be harder to reconstruct from …",
            "url": "https://arxiv.org/abs/2610.36298",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks",
                "summary": "arXiv:2610.36298v1 Announce Type: new \nAbstract: Machine learning models deployed behind query interfaces expose more than their predictions, because an adversary can use those predictions to rebuild the model itself. Model stealing attacks (MSAs) exploit this exposure by training a surrogate model that replicates the decision behavior of a target through black-box queries alone, without access to its parameters or training data. These attacks are well characterized for conventional artificial neural networks (ANNs), yet spiking neural networks (SNNs) process information in a fundamentally different way. SNNs communicate through sparse, discrete spikes, and their outputs depend on membrane potentials that evolve over time rather than on a static mapping from input to output. This temporal mode of computation suggests that the decision behavior of an SNN may be harder to reconstruct from its responses. This work tests that possibility by benchmarking four representative MSAs, namely the Papernot, Tram\\`er, T-RND, and color perturbation attacks, against SNNs and their ANN counterparts on MNIST, Fashion-MNIST, and CIFAR-10. Across every attack and dataset, SNNs prove consistently more difficult to steal. Surrogates of SNNs achieve 10% to 20% lower agreement with the target model and 15% to 25% lower adversarial transferability than surrogates of ANNs. We attribute this resistance to the way SNNs compute, as their spike-based and time-dependent dynamics yield decision boundaries that ANN-based surrogates struggle to approximate, even under large query budgets. These findings extend the known resilience of SNNs beyond attacks on training data to the replication of model functionality, strengthening the case for neuromorphic architectures in security-sensitive applications.",
                "url": "https://arxiv.org/abs/2610.36298",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "467bedf8ff20069e5215c9e4f9f3bdb28ce981d5",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "When Retrieval Is Not Enough: Obsolete Facts in Agent Memory",
            "summary": "arXiv:2610.36308v1 Announce Type: new Abstract: Memory-agent benchmarks often collapse retrieval and answer generation into one score, making it hard to tell whether a failure comes from missing an update or from not using an update that was already retrieved. We examine this distinction on the single-hop FactConsolidation task of MemoryAgentBench. With Qwen2.5-7B-Instruct on 6K-history BM25 accuracy drops from 45% to 32% when the retrieved evidence budget grows from 64 to 512 tokens, even though a gold-assisted post-hoc audit finds the newest statement in every retrieved set. Most of the errors occur on questions that also contain an obsolete statement version. Under a frozen prompt and equal four-statement evidence size, replacing one unrelated statement with the obsolete competing statement reduces accuracy from 100% to 44.6% for Qwen2.5 and from 100% to 87.8% for Qwen3-14B, with all…",
            "url": "https://arxiv.org/abs/2610.36308",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "When Retrieval Is Not Enough: Obsolete Facts in Agent Memory",
                "summary": "arXiv:2610.36308v1 Announce Type: new \nAbstract: Memory-agent benchmarks often collapse retrieval and answer generation into one score, making it hard to tell whether a failure comes from missing an update or from not using an update that was already retrieved. We examine this distinction on the single-hop FactConsolidation task of MemoryAgentBench. With Qwen2.5-7B-Instruct on 6K-history BM25 accuracy drops from 45% to 32% when the retrieved evidence budget grows from 64 to 512 tokens, even though a gold-assisted post-hoc audit finds the newest statement in every retrieved set. Most of the errors occur on questions that also contain an obsolete statement version. Under a frozen prompt and equal four-statement evidence size, replacing one unrelated statement with the obsolete competing statement reduces accuracy from 100% to 44.6% for Qwen2.5 and from 100% to 87.8% for Qwen3-14B, with all 50 harmful paired flips classified as stale. A 32K-history replication likewise favors BM25-64 over BM25-512 (69% versus 58%). These results suggest that retrieving the correct fact is not enough. An obsolete competing statement can be more harmful than an unrelated piece of evidence of the same size.",
                "url": "https://arxiv.org/abs/2610.36308",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "6b0536ded59769c045efc2287ed2a3a5dd632dfb",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Ontology-guided multi-agent reasoning for explainable differential diagnosis",
            "summary": "arXiv:2610.36325v1 Announce Type: new Abstract: Effective differential diagnosis depends on well structured and unambiguous patient case descriptions, since incomplete or ambiguous clinical information readily leads to diagnostic errors and inconsistent reasoning. Large Language Models (LLMs) have recently shown promising capabilities in medical question answering and clinical reasoning; however, even when achieving competitive performance on medical benchmarks, they often rely on pattern recognition learned from training data rather than grounded clinical evidence, and can generate plausible yet unsupported diagnostic conclusions. Their reasoning remains largely opaque, making it difficult for clinicians to assess the evidence and rationale behind a given recommendation. To address this gap, we propose an ontology-guided, multiagent differential diagnosis framework that replicates the …",
            "url": "https://arxiv.org/abs/2610.36325",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Ontology-guided multi-agent reasoning for explainable differential diagnosis",
                "summary": "arXiv:2610.36325v1 Announce Type: new \nAbstract: Effective differential diagnosis depends on well structured and unambiguous patient case descriptions, since incomplete or ambiguous clinical information readily leads to diagnostic errors and inconsistent reasoning. Large Language Models (LLMs) have recently shown promising capabilities in medical question answering and clinical reasoning; however, even when achieving competitive performance on medical benchmarks, they often rely on pattern recognition learned from training data rather than grounded clinical evidence, and can generate plausible yet unsupported diagnostic conclusions. Their reasoning remains largely opaque, making it difficult for clinicians to assess the evidence and rationale behind a given recommendation. To address this gap, we propose an ontology-guided, multiagent differential diagnosis framework that replicates the iterative reasoning process of physicians. The framework grounds diagnostic inference in a structured, expert-curated medical knowledge base, enabling interpretation of symptoms, clinical findings, or disease relationships, while decomposing diagnosis into explicit, auditable reasoning steps. This ontology-based grounding constrains inference to evidence-backed associations, reducing hallucination and improving diagnostic transparency, traceability, and consistency. The system then identifies the most discriminative missing symptoms and generates targeted follow-up questions to reduce uncertainty through a process that mirrors to clinical inquiry. Together, these components improve the reliability, explainability, and diagnostic accuracy of AI-assisted differential diagnosis. The source code is publicly available.",
                "url": "https://arxiv.org/abs/2610.36325",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "d29f63a9acd7cefae3c8632f2c5c275076b700bb",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation",
            "summary": "arXiv:2610.36328v1 Announce Type: new Abstract: Benchmarks for verifiable code generation usually test a proof against one fixed implementation. We ask whether the same proof remains valid after a program refactoring that preserves behavior. We introduce RefactorProof, which derives 458 Lean-certified variants from the 185 VERINA tasks that compile in our pinned environment while holding the specification and evaluated proof fixed byte-for-byte. VERINA supplies reference proofs for 46 tasks, all from its basic split; the primary model-versus-reference comparisons further match on 21-25 short, non-recursive tasks. Structural refactorings expose substantial brittleness across proof sources: task-normalized structural PSR is 4.3% for the supplied references and 13.3-26.8% for the specialized provers. On the matched tasks, specialized prover proofs nevertheless have higher overall unchanged…",
            "url": "https://arxiv.org/abs/2610.36328",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation",
                "summary": "arXiv:2610.36328v1 Announce Type: new \nAbstract: Benchmarks for verifiable code generation usually test a proof against one fixed implementation. We ask whether the same proof remains valid after a program refactoring that preserves behavior. We introduce RefactorProof, which derives 458 Lean-certified variants from the 185 VERINA tasks that compile in our pinned environment while holding the specification and evaluated proof fixed byte-for-byte. VERINA supplies reference proofs for 46 tasks, all from its basic split; the primary model-versus-reference comparisons further match on 21-25 short, non-recursive tasks. Structural refactorings expose substantial brittleness across proof sources: task-normalized structural PSR is 4.3% for the supplied references and 13.3-26.8% for the specialized provers. On the matched tasks, specialized prover proofs nevertheless have higher overall unchanged-proof survival than the supplied reference artifacts: +15.6 points for DeepSeek-Prover-V2-7B, +18.8 for Goedel-Prover-V2-32B, and +20.3 for Goedel-Prover-V2-8B; all three 95% CIs exclude zero. The ordering persists after excluding universally survived T1 variants, under family-balanced aggregation, and under alternative deployable valid-proof selection rules. However, unchanged-proof failure is not the same as high repair cost: predefined one-identifier edits repair 51/54 eligible reference structural failures and 58/85 eligible prover failures. RefactorProof therefore measures unchanged-proof stability under program refactoring, not the cost of maintaining a proof after it breaks.",
                "url": "https://arxiv.org/abs/2610.36328",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "07f7c181f3388871e5a742f88bab889bdccf0faf",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring",
            "summary": "arXiv:2610.36329v1 Announce Type: new Abstract: GPU clusters have become essential computing resources for AI and scientific research in academia and industry. However, their high cost and growing demand often result in long queueing delays. While previous monitoring efforts have operated at second- or minute-level frequencies, they primarily informed job-level scheduling for clusters and lacked the detail needed to optimize GPU-level utilization. This paper presents an in-depth study of a university research GPU cluster, analyzing resource usage at 100 ms intervals. We have developed a lightweight monitoring tool that leverages Nvidia's DCGM library to capture fine-grained \"compute utilization\" metrics within GPUs. Deployed on a cluster with 89 nodes and 319 GPUs, our tool collected data over several months. This paper focuses on a 10-day period with 7,399 jobs submitted by 150 users f…",
            "url": "https://arxiv.org/abs/2610.36329",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring",
                "summary": "arXiv:2610.36329v1 Announce Type: new \nAbstract: GPU clusters have become essential computing resources for AI and scientific research in academia and industry. However, their high cost and growing demand often result in long queueing delays. While previous monitoring efforts have operated at second- or minute-level frequencies, they primarily informed job-level scheduling for clusters and lacked the detail needed to optimize GPU-level utilization.\n  This paper presents an in-depth study of a university research GPU cluster, analyzing resource usage at 100 ms intervals. We have developed a lightweight monitoring tool that leverages Nvidia's DCGM library to capture fine-grained \"compute utilization\" metrics within GPUs. Deployed on a cluster with 89 nodes and 319 GPUs, our tool collected data over several months. This paper focuses on a 10-day period with 7,399 jobs submitted by 150 users from 12 departments. Our study reveals three key findings: (1) the GPU cluster exhibits significant underutilization, with over 70% of jobs using less than 20% of GPU memory and 50% averaging below 5% Streaming Multiprocessor (SM) utilization; (2) 80% of jobs have a drastic mismatch between their requested and actual durations, significantly limiting the scheduler's effectiveness; and (3) the multi-GPU jobs we examined show highly periodic communication patterns. These findings suggest there is plenty of room in the middle: substantial utilization gains are available through better job scheduling and GPU multitasking, independent of hardware or application improvements.\n  Our monitoring solution is available as open-source software at https://github.com/als244/gpu_server_monitoring.",
                "url": "https://arxiv.org/abs/2610.36329",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "73805834b5f2d560aa581424468d6d94f660107a",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning",
            "summary": "arXiv:2610.36335v1 Announce Type: new Abstract: Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporating external information, but often overlooks logical relationships and relies heavily on the LLM's own reasoning, which can compromise answer faithfulness. We propose OA-RAG, an agent that integrates formal reasoning with LLM reasoning, drawing on both the logical structure and informal annotations of domain ontologies. For each answer, OA-RAG reports the ontology observations used as evidence and a model-assessed grounding level (entailed, supported, related, or unrelated) that characterises the strength of that evidence. Across benc…",
            "url": "https://arxiv.org/abs/2610.36335",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning",
                "summary": "arXiv:2610.36335v1 Announce Type: new \nAbstract: Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporating external information, but often overlooks logical relationships and relies heavily on the LLM's own reasoning, which can compromise answer faithfulness. We propose OA-RAG, an agent that integrates formal reasoning with LLM reasoning, drawing on both the logical structure and informal annotations of domain ontologies. For each answer, OA-RAG reports the ontology observations used as evidence and a model-assessed grounding level (entailed, supported, related, or unrelated) that characterises the strength of that evidence. Across benchmarks derived from three large-scale ontologies and six real-world medical question-answering tasks, OA-RAG achieves the best overall performance among the evaluated ontology-fine-tuned and popular RAG methods, with particularly strong results on reasoning-intensive tasks. The reported grounding levels also offer a useful indication of answer reliability, with stronger grounding generally associated with higher accuracy. Finally, our results demonstrate the value of ontologies as knowledge sources: OA-RAG is competitive with, and sometimes outperforms, domain-specific RAG systems that draw on sources such as textbooks.",
                "url": "https://arxiv.org/abs/2610.36335",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "c21287b3f52c8c52432f427d8a39e98ed8dfded5",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)",
            "summary": "arXiv:2610.36341v1 Announce Type: new Abstract: Early AI programs were often also theories of how people think, and programs that wrote programs were, in part, theories of how people program. Here we report on the reanimation of two such programs that offer two seemingly different theories of programming and were developed for quite different purposes. The first, Herbert Simon's Heuristic Compiler (1961), was an experimental model of programming as problem-solving, applying the means-ends analysis methods of the General Problem Solver to investigate the nature of the programming task. The second, KBEmacs (1984), was a working prototype of an intelligent programming assistant developed by MIT's Programmer's Apprentice project, built on the view that expert programmers recognize and combine familiar patterns, or \"cliches.\" It let a programmer build up programs by combining cliches through…",
            "url": "https://arxiv.org/abs/2610.36341",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)",
                "summary": "arXiv:2610.36341v1 Announce Type: new \nAbstract: Early AI programs were often also theories of how people think, and programs that wrote programs were, in part, theories of how people program. Here we report on the reanimation of two such programs that offer two seemingly different theories of programming and were developed for quite different purposes. The first, Herbert Simon's Heuristic Compiler (1961), was an experimental model of programming as problem-solving, applying the means-ends analysis methods of the General Problem Solver to investigate the nature of the programming task. The second, KBEmacs (1984), was a working prototype of an intelligent programming assistant developed by MIT's Programmer's Apprentice project, built on the view that expert programmers recognize and combine familiar patterns, or \"cliches.\" It let a programmer build up programs by combining cliches through a stylized English command language. We approach both through the methodology of Executable Archaeology, the study of historical computational systems by running their original code, a process we call \"reanimation.\" Our reanimation of the Heuristic Compiler reproduces the compiled code appearing in Simon's 1963 paper, and our reanimation of KBEmacs reproduces the SQRT sequence of its December 1984 self-test. Examined side by side, the two theories turn out to have much in common: the Heuristic Compiler also works by adapting existing routines, and Simon later argued that search alone requires a large body of programming knowledge. To highlight the reflexivity of this project, we deliberately used a modern AI-assisted programming tool, Anthropic's Claude Code (Opus 5.5), to carry out much of the detailed reanimation work, building on a significant base of existing software. The explicit, executable theories of programming that both systems embodied are largely absent from today's far more capable AI coding assistants.",
                "url": "https://arxiv.org/abs/2610.36341",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        },
        {
            "id": "0fa11cc9185fc4ec6de6f0e964667faa9c52a861",
            "source_id": "arxiv_ai",
            "source": "arXiv — Artificial Intelligence",
            "category": "ai",
            "engine": "rss",
            "title": "WAKMan: Workload Aware KVCache Manager",
            "summary": "arXiv:2610.36355v1 Announce Type: new Abstract: Prefix caching enables a Large Language Model (LLM) servers to reuse the Key-Value (KV) states and accelerate prefill computation stage for requests that share a prefix with earlier prompts, thus reducing latency and serving cost. With limited memory resource, the KV cache eviction policy becomes a decisive factor in determining the overall benefits of prefix caching. Production traffic may have single-turn, multi-turn, agentic, or a mixture of any combination of these request types. Our findings indicate that agentic steps return within seconds and favor recency, while popular prompts and long conversations return after many other requests and favor frequency. Across 20 mixes, no single policy is always best: vLLM's default strategy LRU provides 12% higher cache hits as compared to the frequency-oriented S3FIFO on agentic-heavy mixes but …",
            "url": "https://arxiv.org/abs/2610.36355",
            "image": "",
            "published": "2026-10-28T04:00:00+00:00",
            "score": 79.75,
            "color": "#b09cff",
            "raw": {
                "title": "WAKMan: Workload Aware KVCache Manager",
                "summary": "arXiv:2610.36355v1 Announce Type: new \nAbstract: Prefix caching enables a Large Language Model (LLM) servers to reuse the Key-Value (KV) states and accelerate prefill computation stage for requests that share a prefix with earlier prompts, thus reducing latency and serving cost. With limited memory resource, the KV cache eviction policy becomes a decisive factor in determining the overall benefits of prefix caching. Production traffic may have single-turn, multi-turn, agentic, or a mixture of any combination of these request types. Our findings indicate that agentic steps return within seconds and favor recency, while popular prompts and long conversations return after many other requests and favor frequency. Across 20 mixes, no single policy is always best: vLLM's default strategy LRU provides 12% higher cache hits as compared to the frequency-oriented S3FIFO on agentic-heavy mixes but trails it by up to 22% elsewhere, and even a single workload parameter can flip the winner even for any particular mix. We present WAKMan, a workload-aware KV cache manager that picks its eviction policy from live traffic without knowing request types or reading prompts. It improves hit rate over LRU by 5 percentage points on average, with the lowest mean and worst-case optimality gap of all policies.",
                "url": "https://arxiv.org/abs/2610.36355",
                "image": "",
                "published": "Wed, 28 Oct 2026 00:00:00 -0400"
            }
        }
    ],
    "stored": 0,
    "ai": {
        "enriched": false,
        "stored": 0
    },
    "health": [
        {
            "id": "arxiv_ai",
            "name": "arXiv — Artificial Intelligence",
            "engine": "rss",
            "category": "ai",
            "ok": true,
            "error": "",
            "ms": 85,
            "count": 20,
            "cached_at": "2026-10-28T18:55:10+00:00"
        }
    ]
}