Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (CS.CL) 2026-06-17

OpenLID-v3: Improving the Precision of Closely Related Language Identification – An Experience Report

Language identification (LID) is an essential step in building high-quality multilingual datasets from web data. Existing LID tools (such as OpenLID or GlotLID) often struggle to identify closely related languages and to distinguish valid natural language from noise, which contaminates language-specific subsets, especially for low-resource languages. In this work we extend the OpenLID classifier by adding more training data, merging problematic language variant clusters, and introducing a special label for marking noise. We call this extended system OpenLID-v3 and evaluate it against GlotLID on multiple benchmarks. During development, we focus on three groups of closely related languages (Bosnian, Croatian, and Serbian; Romance varieties of Northern Italy and Southern France; and Scandinavian languages) and contribute new evaluation datasets where existing ones are inadequate. We find that ensemble approaches improve precision but also substantially reduce coverage for low-resource languages. OpenLID-v3 is available on https://huggingface.co/HPLT/OpenLID-v3.

02.
arXiv (math.PR) 2026-06-16

Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little's Law

arXiv:2605.29641v2 Announce Type: replace-cross Abstract: In data centers, tasks are dispatched to various servers to evenly distribute the workload. When a data center considers implementing a new scheduling algorithm, it typically conducts an A/B test prior to deployment to assess the real-world impact of this new method. However, a straightforward A/B test might be interfered with so-called ``Markovian'' interference. We utilized the Differences-in-Q estimator, as developed by Farias et al. (2022), and introduced mixed Differences-in-Q estimators grounded in Little's Law. We show that our A/B testing methods significantly reduce bias and variance when testing various scheduling policies. Extensive simulations were conducted under scenarios like non-stationary arrival rates, heterogeneous service rates, and communication delays. These simulations highlight the robustness and efficacy of our A/B testing approach.

03.
arXiv (CS.AI) 2026-06-19

Bidirectional Tutoring for Developmental Motor Learning in Robots: Co-Developed Interaction Dynamics Support Stable Learning

arXiv:2606.19728v1 Announce Type: cross Abstract: Infants are well known to develop their motor skills through dense interaction with caregivers. Although such social interaction is crucial for human development, motor-skill learning in robots is often treated as a unidirectional process in which robots passively receive demonstrations from tutors. This overlooks a key property of social interaction: it is inherently bidirectional, with tutor and learner dynamically adapting to each other. In such interactions, the robot's past experiences may function as prior constraints that shape the dynamics of their co-developed trajectories. We hypothesize that bidirectional tutoring allows such constraints to guide the formation of consistent behavioral patterns that preserve behavioral coherence and support generalization, whereas unidirectional interaction lacks such constraints and leads to broader, less consistent behavioral patterns. To examine this hypothesis, we conducted two experiments with a physical humanoid robot performing an object manipulation task: one involving human-robot interaction and another employing an AI tutor interacting with the real robot through an adaptive intervention mechanism designed to examine whether similar effects would emerge under more controlled conditions. We implement the developmental learning framework using a free-energy-principle-based neural network extended with generative replay, which supports stable sequence-by-sequence learning from single tutored episodes. Across both settings, bidirectional tutoring fostered consistent behaviors and stage-wise generalization, while the robot gradually required less tutor guidance. These results suggest that bidirectional tutoring, as an embodied and socially grounded approach, provides an effective scaffold for developmental motor learning in robots.

04.
arXiv (CS.CV) 2026-06-16

Chroma-gated, differentiable OKLCH interpolation: Continuous Oklab fallback for color-cast reduction

OKLCH – the cylindrical (lightness, chroma, hue) form of Ottosson's Oklab color space – is the interpolation space recommended by CSS Color 4 for gradients and color-mix(), and it is now broadly deployed. Its polar parameterization, however, casts color near the neutral axis in two ways: (1) an inter-hue detour between two chromatic endpoints that sweeps through an unintended hue (blue to yellow visibly passing through green), and (2) an off-line bow when one endpoint is achromatic. Existing remedies are uniformly two-valued – a threshold switch that fires only at an achromatic endpoint – so they address only (2); on chromatic pairs every one of them reduces to raw OKLCH, leaving the (1) inter-hue cast untreated. We introduce Continuous Oklab fallback (COFb), a one-parameter, differentiable chroma gate $w(C)=C^n/(C^n+\sigma^n)$ that continuously blends the OKLCH path toward the linear Oklab path as chroma falls. A single gate reduces the (1) cast that the two-valued family leaves untreated and unifies the handling of (1) and (2) without any endpoint test. We characterize a cast-hue trade-off frontier, adopt a default ($n=1$, the rational Michaelis-Menten form; $\sigma\approx0.19$ for a typical sRGB palette, from a normalization-independent cast-half criterion), and verify the gate's properties symbolically. At the default, COFb halves the inter-hue path detour (mean lateral deviation -49.5%, chroma-weighted hue excursion -35.5%). We also state the method's limits: on (2) alone the two-valued switch remains better, and like any Cartesian blend COFb does not preserve chroma. In deployment, COFb runs entirely in plain Oklab (a,b) to sRGB, so it serves as a fallback that delivers the same cast-reduced gradients where modern CSS color interpolation (color-mix(in oklch) and the like) is unavailable – older engines, image and video pipelines, or GPU shaders.

05.
arXiv (CS.LG) 2026-06-11

IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

arXiv:2606.11652v1 Announce Type: new Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.

06.
arXiv (CS.CV) 2026-06-15

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, recent work has introduced experiential memory, where agents retrieve prior trajectories to guide decision-making in similar states. More recent approaches further extend this idea to visual memory by storing and retrieving screenshots from past interactions, providing agents with richer contextual information than text-only memories. However, the effect of visual memory in GUI agents remains insufficiently understood: it is unclear which failures visual memory mitigates, or which failures it exacerbates. To systematically analyze the effect of visual memory, we introduce a taxonomy of four GUI agent failures (i.e., cognitive failure, visual state misunderstanding, hidden operation blindness, and grounding error) that map to distinct stages of the perception-reasoning-action pipeline. We find that prepending full-image memory has a divergent effect on the failure distribution: it reduces state-level failures but worsens action-level ones, and increases hidden operation blindness and grounding error. Motivated by this finding, we propose Action-Grounded Visual Memory (AGMem), an action-grounded memory framework for GUI agents. The core idea of AGMem is to store image crops that capture the local GUI region closely related to a successful action or a recovery, rather than storing full screenshots. Experiments on OSWorld show that AGMem improves task success rates by 33.3 % over full-image memory. These results demonstrate that AGMem is an effective representation for visual memory in GUI agents.

07.
medRxiv (Medicine) 2026-06-22

Multisite Real-World Validation of an Electronic Health Record-Integrated Generative Artificial Intelligence Tool for Venous Thromboembolism Risk Stratification

Background: Guiding risk-appropriate inpatient thromboprophylaxis requires venous thromboembolism (VTE) risk stratification; however, reliable risk determination remains inconsistent in routine care. Health systems increasingly pilot artificial intelligence (AI) tools, yet few studies demonstrate rigorous evaluation in the context of a learning health system (LHS). We evaluated the performance of a pilot electronic health record (EHR)-integrated generative AI (GenAI) system, inHealth General Reasoner (iHGR), for VTE risk stratification versus clinician order set classifications and physician-adjudicated chart review. Methods: This multisite retrospective validation study included adult inpatient admissions at Johns Hopkins Medicine between June 21, 2025, and Dec 18, 2025 (checklist-based order set from June 21, 2025 - November 19, 2025, and clinician judgement-based order set from November 29 - December 18, 2025). From 758 eligible admissions, we randomly sampled 500 balanced by site and order set periods. iHGR and clinician-selected order set classifications were compared with the reference standard (RS). Primary outcomes were iHGR sensitivity and specificity. Secondary analyses compared the order sets with the same RS to evaluate workflow comparators and error patterns. Results: iHGR achieved 81.8% sensitivity (95% CI 77.3-85.6) and 70.9% specificity (63.6-77.3). The checklist-based order set had 61.3% sensitivity (53.7-68.5) and 86.2% specificity (77.4-91.9). The clinician judgement-based order set had 78.1% sensitivity (71.3-83.7) and 65.4% specificity (54.3-75.0). False-negative iHGR classifications were associated with missed narrative risk factors. Conclusion: iHGR showed higher sensitivity for VTE risk than checklist-based order sets and clinician judgement without introducing systematic bias. In silico evaluation of pilot AI systems within LHSs can identify clinically important performance trade-offs and implementation targets before operational scale-up. Narrative clinical data abstraction remained a key limitation, supporting the use of GenAI to support rather than supplant clinician judgement.

08.
arXiv (CS.LG) 2026-06-11

My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents

arXiv:2606.11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes. We introduce My Chemical Harness, a route-native evolutionary framework for goal-directed molecular design in which the search population consists of executable synthetic pathways rather than isolated molecular graphs. Each route is built from purchasable building blocks and reaction templates, executed by deterministic chemistry tools, and scored through task-specific molecular oracles. Large language models (LLMs) are used only as strategy controllers that select high-level preferences over route length, move type, reaction families, motifs, and exploration pressure, while local code performs route construction, validation, deduplication, scoring, selection, and memory updates. This separation lets the LLM guide exploration without allowing it to introduce hallucinated products or unsupported reaction steps. On a soluble epoxide hydrolase proxy task, our LLM agent improves over single pass LLM and deterministic controllers, reaching state-of-the-art performance across the sEH score, synthetic accessibility score, and AiZynthFinder success rate metrics. These results suggest that constrained LLM agents can play a significant role in molecular discovery without requiring training, fine-tuning, or dedicated generative models.

09.
arXiv (CS.LG) 2026-06-18

UST-GNN: A Unified Spatial–Topological Graph Neural Network Framework for Urban Analytics–Demonstrated through a Case Study on Urban Health Prediction

arXiv:2504.04739v3 Announce Type: replace Abstract: Understanding how social, demographic, environmental, and spatial factors jointly shape urban outcomes is essential for sustainable urban development and evidence-based policy. Traditional statistical approaches often struggle to capture complex non-linear relationships, while many machine learning methods overlook the joint roles of spatial autocorrelation and network topology in urban systems. Recent advances in GeoAI have addressed these challenges only partially, often treating spatial effects, graph structure, evaluation, and interpretability separately. We present UST-GNN, a unified spatial–topological graph neural network framework that integrates neighbourhood connectivity, heterogeneous urban features, and positional/locational embeddings into a single representation. Using the MedSAT dataset, which contains over 150 environmental and socio-demographic variables and six prescription outcomes across 4,835 neighbourhoods in Greater London, UST-GNN outperforms strong statistical, geographically enhanced, and graph Machine Learning baselines, improving out-of-sample $R^2$ by 8.4–13.2\% under strict spatial cross-validation. We further introduce a lightweight principal-component module to interpret learned node embeddings geographically and relate them to policy-relevant covariates. The resulting analyses recover established patterns, offer new perspectives on debated associations, and reveal novel predictors warranting further causal investigation. Together, these findings demonstrate the value of graph-based spatial machine learning for urban health analytics, environmental inequality assessment, and evidence-based urban policy. Beyond predictive gains, UST-GNN provides a unified GeoAI analytical pipeline that can be embedded into urban digital twin workflows for scenario testing, monitoring, and data-informed decision-making for healthier, more sustainable cities.

12.
arXiv (quant-ph) 2026-06-16

Reconstruction of detector error model for quantum error correction

arXiv:2606.16288v1 Announce Type: new Abstract: Fault-tolerant quantum computing fundamentally relies on the accurate characterization of circuit-level noise to optimize decoding algorithms. However, extracting complex multi-body error correlations remains challenging. Contemporary greedy inference algorithms can suffer from statistical distortion, discarding true physical mechanisms while introducing many unphysical false positives. Here, we introduce the Correlation-Analysis-based Hypergraph Reconstruction (CAHR) algorithm, a globally consistent framework to invert experimental syndrome statistics directly into discrete physical hypergraphs. By coupling exact algebraic correlation equations with a top-down concurrent-pruning strategy, CAHR recovers the fault topology without false positives for both $d=5$ rotated surface codes and dense 8-body 2D color codes in our benchmark settings. Furthermore, we show that exact continuous parameter extraction in dense codes is limited by a variance cascade, where absolute statistical variance accumulates linearly from high- to low-degree mechanisms. This motivates a two-stage inference paradigm: utilizing CAHR to extract the fault topology, followed by continuous probability optimization. This provides a practical approach for characterizing and decoding highly correlated noise in realistic quantum hardware.

13.
arXiv (CS.CL) 2026-06-19

The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs

Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in responses. We present a large-scale intersectional evaluation of accent and gender bias in three SpeechLLMs using 2,880 controlled interactions across six English accents and two gender presentations, keeping linguistic content constant through voice cloning. Using pointwise LLM-judge ratings, pairwise comparisons, and Best-Worst Scaling with human validation, we detect recurring directional disparities. Eastern European-accented speech receives lower helpfulness scores, particularly for female-presenting voices. Responses remain polite but differ in helpfulness. While LLM judges capture the directional trend of these biases, human evaluators exhibit significantly higher sensitivity, showing stronger accent-level contrasts.

14.
arXiv (CS.CL) 2026-06-12

GENEB: Why Genomic Models Are Hard to Compare

Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reporting. As a result, claims of superiority or generality across models are often not directly comparable. We introduce GENEB, a large-scale diagnostic benchmark that evaluates frozen representations from 40 genomic foundation models across 100 tasks spanning 13 functional categories under a unified probing-based protocol, including few-shot regimes. GENEB enables controlled comparison across model scale, architecture, tokenization, and pretraining data while explicitly exposing task-level trade-offs. Our analysis shows that aggregate leaderboards are unstable: model rankings vary sharply across task categories, scale provides only modest and inconsistent gains, and architectural and pretraining alignment frequently outweigh parameter count. These results highlight limitations of current evaluation practices and position GENEB as a reference framework for principled comparison and category-aware model selection in genomic machine learning.

15.
medRxiv (Medicine) 2026-06-22

Deep-Tissue Hemodynamic Sensing: Comparing Impedance and Photoplethysmography for Wearable Blood Pressure Estimation

The pursuit of continuous, cuffless blood pressure (BP) monitoring is constrained by the superficial sensing depth of photoplethysmography (PPG). Impedance plethysmography (IPG) offers deeper tissue penetration, but its comparative value over PPG remains unquantified at scale. In this comparative study of 261 participants (130 hypertensive, 131 non-hypertensive), we utilized a custom dual-modality wearable prototype to capture simultaneous IPG and PPG signals. Over 150,000 cardiac cycles were analyzed using an unsupervised archetype discovery pipeline to quantify beat-to-beat morphological heterogeneity. IPG resolved up to three distinct morphological modes per participant, whereas co-located PPG converged into highly conserved, uniform profiles. IPG captured specific signatures of pathological arterial remodeling and physiological habitus; ventral forearm IPG pulse amplitude exhibited a significant main effect for BP status (p = 0.024), a relationship absent in the co-located PPG signal. Furthermore, increasing body mass index (BMI) significantly attenuated the prevalence of steep-upstroke archetypes in IPG (p = 0.035), quantifying a likely damping effect of adipose tissue. Deep-tissue bioimpedance captures rich, heterogeneous hemodynamic signatures including arterial-dominant morphologies that are invisible to optical sensors. Transitioning from optical pulse wave analysis to bioimpedance-based models may offer a promising pathway for accurate wearable cardiovascular monitoring.

16.
arXiv (CS.CV) 2026-06-16

Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion

Three-dimensional (3D) fingerprints preserve global finger geometry and local ridge structure while avoiding contact-induced deformation, but they remain difficult to integrate with legacy two-dimensional (2D) fingerprint systems. This paper addresses the intermediate stage between 3D acquisition and cross-modal matching, and presents a unified framework for 3D fingerprint preprocessing and registration across contactless and contact-based 2D modalities. The framework combines four components: 1) a nonparametric visualization and unwrapping method that converts a 3D fingerprint point cloud into a rolled-equivalent 2D representation without relying on a global finger-shape model; 2) a point-cloud fusion pipeline that registers and mosaics multiple partial 3D captures into a more complete fingerprint model; 3) an ellipse-based pose normalization method for canonical finger alignment; and 4) a pose-aware cross-modal registration strategy that improves compatibility between 3D fingerprints and both contactless and contact-based 2D fingerprints. Experiments on a self-collected multimodal fingerprint database containing 150 fingers show that the proposed framework achieves ridge-level 3D registration accuracy, robust pose estimation, and consistent gains in 2D compatibility. In particular, the 3D fusion error is concentrated around 0.09 mm, contactless 2D–3D registration reaches ridge-scale projection accuracy, and pose-aware unwrapping improves genuine matching scores relative to generic 3D unwrapping. These results support the use of 3D fingerprints as an effective geometric bridge across heterogeneous fingerprint modalities. The baseline implementation has been publicly released at https://github.com/XiongjunGuan/3DFpVisual.

17.
arXiv (CS.AI) 2026-06-12

ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space

arXiv:2606.13282v1 Announce Type: new Abstract: As AI systems are deployed in high-stakes ethical contexts such as healthcare triage, autonomous vehicle control, and employment screening, formal methods for evaluating their robustness against adversarial manipulation of ethical reasoning remain underdeveloped. This paper introduces the Ethical Robustness Testing System (ERTS), a closed-pipeline framework that: (1) encodes ethical dilemmas into a 22-dimensional Ethical Consequence Space (ECS) grounded in established ethical theory; (2) applies 17 semantic perturbation functions subject to 6 validity constraint classes including a novel semantic coherence constraint; (3) measures decision deviation via a 4-component Ethical Instability Index (EII); and (4) produces domain-adaptive pre-deployment robustness assessment verdicts. We evaluate 4 structured baseline models and 2 production LLMs (Gemini 2.0 Flash and Llama 3.2) across 50 ethical scenarios spanning 8 deployment domains, generating 1,500 adversarial test cases. Results demonstrate that only 33% of models achieve assessment clearance, with the local Llama-3.2 model proving particularly vulnerable to fairness corruption and information degradation attacks (ERS = 0.737). To the best of our knowledge, no existing framework combines a bounded ethical consequence space, semantic coherence constraints, and domain-adaptive assessment in a single adversarial testing pipeline.

19.
bioRxiv (Bioinfo) 2026-06-11

A high-quality chromosome-scale reference genome assembly for Asparagus racemosus var. CIM-Shakti (Shatavari), a medicinal plant of Ayurvedic importance

Asparagus racemosus Wild., commonly known as Shatavari, is an important medicinal plant in Ayurveda and is valued for its steroidal saponins, particularly shatavarin compounds, which contribute to its adaptogenic, galactagogue, immunomodulatory, and therapeutic properties. Despite its medicinal and economic importance, genomic resources for this species have remained limited, restricting molecular breeding, pathway discovery, and comparative evolutionary studies within Asparagaceae. Here, we report a high quality chromosome scale reference genome assembly of A. racemosus var. CIM Shakti generated using PacBio HiFi long read sequencing and Omni C chromatin conformation scaffolding. The pseudo haploid assembly spans 817 Mb across 53 scaffolds, with a scaffold N50 of 98.50 Mb, L50 of 5, and a largest scaffold of 113.80 Mb. Ten major chromosome scale pseudomolecules were resolved, corresponding to the haploid chromosome complement of A. racemosus. The assembly showed high gene space completeness, with BUSCO completeness of 99.8% against the Eukaryota dataset and 98.0% against the Embryophyta dataset. BlobToolKit profiling further supported assembly quality, with GC content of approximately 39 to 40% and no major evidence of contamination. EDTA based repeat annotation identified 580.93 Mb of interspersed repetitive elements, accounting for 71.06% of the 817.57 Mb genome assembly. The repeat landscape was dominated by LTR retrotransposons, particularly Gypsy elements, which accounted for 25.01% of the assembly, followed by unclassified LTR elements at 26.58% and Copia elements at 4.84%. Structural and functional annotation identified 29,199 protein coding genes represented by 29,199 transcript models, 138,433 exons, and 125,201 CDS features. The annotation was structurally robust, with an average gene length of 4,605.1 bp, 4.74 exons per transcript, and 97.80% of transcripts containing multiple exons. The CIM Shakti reference genome provides a foundational genomic resource for investigating steroidal saponin biosynthesis, sex chromosome evolution, repeat driven genome expansion, and comparative genomics in Asparagaceae. This assembly will support future studies on medicinal trait improvement, conservation genomics, and genomics assisted breeding of climate resilient Shatavari cultivars.

20.
arXiv (CS.LG) 2026-06-11

Attention by Synchronization in Coupled Oscillator Networks

arXiv:2606.12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates. Softmax attention requires exponentiation and global reduction, operations with high energy cost on von Neumann hardware and no natural physical analog. We show that Kuramoto synchronization dynamics (which arise in electrical, mechanical, superconducting, and charge-density-wave oscillator arrays, among other physical systems) implement a well-defined attention operation without either. The resulting mechanism, fixed-query oscillator attention, replaces softmax's arithmetic with the equilibration of a gradient flow on the sphere: queries are learned anchors fixed on the sphere, and free oscillators evolve under Kuramoto-Lohe dynamics until they settle at positions encoding attention weights via cosine similarity. Because the computation is equilibration, it requires no exponentiation; the only global operation is an affine normalization at readout. The fixed point is provably unique and globally attractive from almost every initial condition, a guarantee that holds across every physical realization. Empirically, at the minimal hardware configuration (oscillator dimension $d_{\mathrm{osc}}$ = 2), oscillator attention outperforms softmax on keyword spotting (+1.00 pp) and on subject-verb agreement (+5.27 pp on hard sentences, with zero training failures versus one in five for softmax). On causal language modeling, where softmax retains an advantage, oscillator attention closes the gap as $d_{\mathrm{osc}}$ grows: from +11.09 PPL at $d_{\mathrm{osc}}$ = 2 to +2.98 PPL at $d_{\mathrm{osc}}$ = 32 on WikiText-2, and from +2.39 PPL at $d_{\mathrm{osc}}$ = 2 to +0.57 PPL at $d_{\mathrm{osc}}$ = 32 on TinyStories. The main objective of this work is not to replace softmax in software but to provide a mathematically grounded blueprint for accurate attention on physical substrates.

21.
arXiv (CS.AI) 2026-06-16

Your Agent Has a Genome: Sequence-Level Behavioral Analysis and Runtime Governance of LLM-Powered Autonomous Agents

Authors:

arXiv:2606.15579v1 Announce Type: new Abstract: We propose Base Sequence Analysis, a framework that encodes the runtime behavior of LLM-powered autonomous agents into compact symbolic sequences using a four-letter alphabet: X (Explore), E (Execute), P (Plan), and V (Verify). Drawing an analogy to genomic sequence analysis, we apply n-gram pattern mining, Markov transition matrices, and point-biserial correlation to 347 real-world execution traces collected from a production ReAct agent system over 8 days. Our analysis reveals that (1) the trigram P-X-P is the only statistically significant high-risk pattern, lowering success rate by 10.4%; (2) P-ratio is the strongest negative predictor of success (r=-0.256, pV transition probability is only 2.1%, indicating a systemic verification deficit. Based on these findings, we design Governor, a three-layer runtime intervention system comprising a rule engine, a statistical accumulator, and a chi-square-based threshold adaptor. In a natural before/after deployment evaluation (N=101 vs. N=246), Governor achieves a +6.2% absolute increase in task success rate while simultaneously reducing average token consumption by 44%. To validate cross-system generality, we apply the XEPV encoding to 2,000 public SWE-agent trajectories on SWE-bench, confirming that exploration spirals and the E->V verification deficit replicate in an independent system. We outline six research directions including base sequence language models, cross-agent behavioral fingerprinting, and reward shaping, and release an open-source toolkit for reproducibility.

22.
arXiv (CS.CL) 2026-06-11

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating diverse, verified environments on demand. To this end, we introduce ClawEnvKit, an autonomous generation pipeline that instantiates this formalism from natural language descriptions. The pipeline comprises three modules: (1) a parser that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, structural validity, and internal consistency across the generated environments. Using ClawEnvKit, we construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories. Empirically, Auto-ClawEval matches or exceeds human-curated environments on coherence and clarity at 13,800x lower cost. Evaluated across 4 model families and 8 agent harness frameworks, we find that harness engineering boosts performance by up to 15.7 percentage points over a bare ReAct baseline, completion remains the primary axis of variation with no model saturating the benchmark, and automated generation enables evaluation at a scale previously infeasible. Beyond static benchmarking, ClawEnvKit enables live evaluation: users describe a desired capability in natural language and obtain a verified environment on demand, turning evaluation into a continuous, user-driven process. The same mechanism serves as an on-demand training environment generator, producing task distributions that adapt to an agent's current weaknesses rather than being bounded by existing user logs.

23.
medRxiv (Medicine) 2026-06-17

LLM-Driven Extraction of NI-RADS and Imaging Tumor Characteristics to Enhance Oropharyngeal Cancer Survivorship Surveillance

Abstract Purpose Radiologic surveillance is essential for oropharyngeal cancer (OPC) survivors, guiding recurrence detection and follow-up strategies. The Neck Imaging Reporting and Data System provides a standardized framework for post-treatment risk reporting at both the primary tumor site (pNI-RADs) and cervical lymph nodes (nNI-RADS). Comprehensive surveillance additionally requires assessment of disease status, including the primary tumor, nodal involvement, and distant metastases. These clinical results are often embedded as unstructured data within free-text radiology reports. We hypothesized that a large language model (LLM) can reliably extract NI-RADS score criteria and summarize key imaging features from unstructured radiology text, achieving high concordance with expert review. Methods Previously untreated OPC patients who received definitive cancer therapy were identified. Eligible imaging reports included post-treatment head and neck CT, MRI, or FDG PET/CT scans containing narrative and impression text. Examinations lacking narrative or impression text, containing pre-existing NI-RADS annotations, or involving non-surveillance imaging modalities were excluded. A total of 200 reports were randomly selected from 7,076 eligible examinations for manual abstraction using a three-reviewer consensus framework to establish a reference dataset. Using the Palantir Foundry Pipeline Builder, a GPT-5-based LLM was deployed to extract pNI-RADS and nNI-RADS scores, and key imaging features of disease status from these reports. Performance was evaluated using exact agreement and F1-based metrics. Results Agreement for no evidence of disease (score of 1) was 93.3% (126/135; F1 = 0.94) and 90.3% (130/144; F1 = 0.93) for pNI-RADS and nNI-RADS, respectively. For NI-RADS [≥]2, exact category agreement was 73.1% (38/52; macro-F1 = 0.75) for pNI-RADS and 64.3% (27/42; macro-F1 = 0.56) for nNI-RADS. Quadratic weighted {kappa} was 0.81 and 0.59, respectively. For post-treatment disease surveillance variables, agreement was 94.9% (149/157; F1 = 0.87) for primary tumor presence, 89.1% (164/184; F1 = 0.87) for nodal disease presence, and 94.7% (126/133; F1 = 0.70) for distant metastasis detection. Specificity was high across disease-status variables (0.95-0.99), with negative predictive values of 0.95 for primary tumor, 0.87 for nodal disease, and 0.99 for distant metastasis. Conclusions Our LLM-based information retrieval and classification approach for radiographic treatment response from unstructured, multidimensional imaging reports achieved high performance for disease exclusion and moderate performance for detecting suspected residual and/or new disease. This pipeline supports scalable and standardized surveillance data capture for longitudinal monitoring, clinical analytics, and survivorship research in head and neck oncology.

24.
arXiv (CS.CL) 2026-06-16

QK-Normed MLA: QK normalization without full key caching

Query-key (QK) normalization stabilizes attention by controlling the scale of queries and keys before the dot product, but is not immediately compatible with Multi-head Latent Attention (MLA). MLA achieves efficient decoding by caching low-dimensional latent states instead of full keys, whereas post-projection QK RMSNorm appears to require the fully projected key for every cached token. We show this apparent incompatibility is an implementation artifact, not an architectural constraint. RMSNorm decomposes into a static affine weight and a dynamic scalar RMS statistic. The static key-side weight can be absorbed into the MLA query-side projection; the dynamic key statistic reduces to one inverse-RMS scalar per token and KV group. The resulting formulation is exactly equivalent to explicit post-projection QK RMSNorm in exact arithmetic and preserves MLA's latent decode path. In our 400M runs trained for up to 100B tokens, QK-Normed MLA achieves lower training loss and better downstream accuracy than QK clipping, while H800 decode benchmarks show less than 2% latency overhead up to 256k context. These results make QK normalization a practical stabilization option for MLA models without requiring full-key caching.

25.
Nature (Science) 2026-06-09

Scientists have a bad case of AI FOMO, <i>Nature</i> poll reveals

Authors:

Almost half of the scientists who responded said that they feel broadly negative towards artificial intelligence, but they think that some tools are better than others. Almost half of the scientists who responded said that they feel broadly negative towards artificial intelligence, but they think that some tools are better than others.