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.
medRxiv (Medicine) 2026-06-15

Wellbeing After Stroke-2 (WAterS-2): a feasibility study with process evaluation exploring inclusive, accessible, online psychological support after stroke

Objectives: Explore feasibility and acceptability of upskilling a workforce to deliver a co-developed intervention, based on Acceptance and Commitment Therapy (ACT), to support psychological adjustment post-stroke targeting underserved groups. Design: Multi-site, single-arm feasibility study with embedded mixed-methods process evaluation (ISRCTN17628580). Setting: Four NHS community stroke services across England. Participants: 1. Stroke survivors [≥]18 years of age, [≥]4 months post-stroke, reporting psychological difficulties adjusting to stroke, able to consent and access remote group sessions in English; 2. Group facilitators from NHS stroke services, not ACT specialists. Intervention: WAterS-2: an eight-session, remotely-delivered ACT-informed group intervention. Outcome measures: Recruitment, fidelity, safety, acceptability and perceived value were assessed using fidelity checklists, post-intervention surveys and semi-structured interviews with stroke survivors and facilitators. Clinical outcomes including mood (HADS), wellbeing (ONS4), psychological flexibility (AAQ-ABI), measured post-group and three-months later. Results: Nineteen stroke survivors recruited (mean 9.6 months post-stroke; n=5 (26%) minoritised ethnicities; n=10 (52%) with aphasia). Thirteen facilitators - including two peer support workers - delivered the intervention with fidelity following structured training across four services. Drop-out was low (2/19; 11%); with 15 (79%) attending [≥]5/8 sessions. Remote data collection was feasible (79% follow-up completion), with no adverse events recorded. Acceptability was high: survivors valued peer connection, grounding and mindfulness practices. ACT metaphors were helpful for some but challenging for others, including some with aphasia. Online delivery was suitable but limited informal connection. Facilitators reported increased capability, incorporating ACT skills into routine care. NHS workforce pressures and geographically-constrained referral pathways limited recruitment reach. Conclusions: WAterS-2 is feasible, safe, acceptable and inclusive. A mixed workforce, including NHS peer support workers, can be upskilled to deliver with fidelity. Inclusion of underserved groups is achievable but requires active strategies beyond standard NHS referral routes. Findings inform a provisional logic model and a future pragmatic trial.

02.
arXiv (CS.LG) 2026-06-15

Adaptive Nucleus Truncation for Long-Form Reasoning

arXiv:2606.13982v1 Announce Type: cross Abstract: Sampling plays an important role in long-form language-model reasoning. Over thousands of decoding steps, small changes in the candidate token set can compound into different reasoning trajectories, stability profiles, and final answers. Existing truncation methods such as top-$p$, min-$p$, and fixed top-$n\sigma$ sampling improve over unrestricted sampling, but they rely on fixed thresholds that cannot adapt to changes in entropy, task difficulty, training stage, or generation budget. We introduce Adaptive Nucleus Truncation Sampling (ANTS), which extends top-\(n\sigma\) sampling from a fixed decoding rule into an adaptive rollout-control mechanism for long-form generation. ANTS selects standardized neighborhoods around the maximum logit before temperature scaling, adapts the truncation width using an entropy-conditioned controller, and retains a no-truncation fallback arm to stabilize training when truncation becomes unsafe. On a 33B-total / 4B-active sparse Mixture-of-Experts reasoning model, ANTS improves average performance over percentage-based benchmarks by +1.9, +3.8, and +5.2 points at 8K, 16K, and 32K generation budgets, respectively. The strongest gains appear on instruction following and mathematical reasoning, with IFBench improving by more than 10 points at 32K and AIME 2025 improving by 7 points. Code generation reveals an important budget interaction. On Codeforces, ANTS trails the baseline at 8K, but reverses this gap and substantially improves ELO at 16K and 32K. These results suggest that sampler design should be treated not just as a decoding hyperparameter, but as part of how we stabilize and scale long-budget reasoning.

03.
arXiv (CS.CL) 2026-06-15

Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal

Deployed language models must decide not only what to answer but also when not to answer. We present UniCR, a unified framework that turns heterogeneous uncertainty evidence including sequence likelihoods, self-consistency dispersion, retrieval compatibility, and tool or verifier feedback into a calibrated probability of correctness and then enforces a user-specified error budget via principled refusal. UniCR learns a lightweight calibration head with temperature scaling and proper scoring, supports API-only models through black-box features, and offers distribution-free guarantees using conformal risk control. For long-form generation, we align confidence with semantic fidelity by supervising on atomic factuality scores derived from retrieved evidence, reducing confident hallucinations while preserving coverage. Experiments on short-form QA, code generation with execution tests, and retrieval-augmented long-form QA show consistent improvements in calibration metrics, lower area under the risk-coverage curve, and higher coverage at fixed risk compared to entropy or logit thresholds, post-hoc calibrators, and end-to-end selective baselines. Analyses reveal that evidence contradiction, semantic dispersion, and tool inconsistency are the dominant drivers of abstention, yielding informative user-facing refusal messages. The result is a portable recipe of evidence fusion to calibrated probability to risk-controlled decision that improves trustworthiness without fine-tuning the base model and remains valid under distribution shift.

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

How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of translation errors. In this work, we focus on extrinsic discourse evaluation of machine translation under two distinct regimes: static and interactive. Under the static regime, we propose an entity counting task as a probe of referential consistency in discourse. We show that high intrinsic MT quality does not reliably predict downstream discourse success and strong MT systems still produce referential inconsistencies. For the interactive regime, we study the goal-oriented multi-agent Welfare Diplomacy game as a probe of long-horizon communication and coordination. We find that interaction-specific translation failures impact downstream coordination. Our results highlight goal-oriented environments as a viable framework for discourse-sensitive extrinsic MT evaluation.

05.
arXiv (CS.AI) 2026-06-16

Probing Low Frame Rate Degradation in Neural Audio Codecs

arXiv:2606.16969v1 Announce Type: cross Abstract: Low frame rates in neural audio codecs are attractive for autoregressive speech synthesis, where the generation cost scales linearly with the sequence length. Recent work has demonstrated that codecs can operate at 12.5 Hz and below, but the mechanisms underlying low frame rate degradation remain insufficiently understood. We investigate these mechanisms through a controlled frame rate ablation. We reproduce a quality cliff at 6.25 Hz reported in previous works and evaluate candidate explanations: phonemic collisions and codebook saturation, neither of which shows evidence of a fundamental barrier. The cliff is instead caused by suboptimal training configuration: fixed clip duration during training yields too few tokens at low frame rates, starving the decoder of inter-token context. Once corrected, WER degrades smoothly with phonemic load down to 3.1 Hz and 1.6 Hz, suggesting the inference-time efficiency gains of low frame rate codecs are more accessible than previously assumed.

07.
arXiv (CS.LG) 2026-06-19

FloatDoor: Platform-Triggered Backdoors in LLMs

arXiv:2606.19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has shown that an identical model can produce measurably different outputs depending on the deployment platform, a consequence of non-associative floating-point arithmetic and divergent kernel implementations. We study the security implications of this platform-dependent variability and uncover a novel attack surface on LLM deployments. We introduce FloatDoor, the first input-independent, platform-triggered backdoor attack against generative LLMs. The compromised model exhibits adversary-chosen behavior when served on a target platform and is otherwise benign. FloatDoor is realized through two lightweight LoRA adapters, one that amplifies inter-platform numerical divergence and one that binds the resulting platform signature to a malicious downstream task, while leaving aggregate model utility largely intact. FloatDoor exploits a pronounced time-of-check, time-of-use gap between model auditing and serving. We demonstrate FloatDoor on Qwen3-4B across a broad range of deployment targets, including NVIDIA GPUs, Google TPUs, AWS Graviton, and Alibaba Yitian-710. As a final case study, we show that FloatDoor reliably induces exploitable code vulnerabilities on a chosen target platform. Our results establish a new class of attacks on LLM deployments and underscore the pressing need for trusted model supply chains in sensitive, LLM-powered applications.

08.
arXiv (quant-ph) 2026-06-24

Flexible Catalysis

arXiv:2510.01065v2 Announce Type: replace Abstract: In quantum information and computation, a central challenge is to determine which quantum states can be transformed into which others under restricted sets of free operations. While many transformations are impossible directly, catalytic processes can enable otherwise forbidden conversions: an auxiliary quantum state (the catalyst) facilitates the transformation while remaining unchanged. In this work, we introduce flexible catalysis, a generalization in which the catalyst is allowed to transform into a different auxiliary state, provided it remains a valid catalyst. We show that this framework subsumes both standard catalytic and multicopy transformations, and we analyse its advantages across several classes of free operations. In particular, we prove that when the free operations are local unitaries or permutation matrices, flexible catalysis enables state extractions that are unattainable with standard catalysis alone.

10.
PLOS Computational Biology 2026-06-17

Deciphering cell type-specific causal genetic effects on brain imaging-derived phenotypes and disorders with single-cell Mendelian randomization

Authors:

by Anyi Yang, Xingzhong Zhao, Xing-Ming Zhao, Yucheng T. Yang Reconstructing causality routes from genetic effects to complex phenotypes in particular cell types is crucial for understanding biological mechanisms underlying the brain-associated phenotypes including imaging-derived phenotypes (IDPs), and brain disorders and behaviors (DBs). Here, we develop a single-cell Mendelian randomization framework to infer cell type-specific causal relationships between gene expression and diverse brain-associated complex phenotypes by integrating single-cell expression quantitative trait loci (cis-eQTLs) and genome-wide association study findings. We identifiy a set of 254 and 217 cis-eQTL target genes (eGenes) that may have causal effects on 112 IDPs and 26 DBs in eight cell types, respectively. These causal eGenes exhibit strong cell type specificity and varied pleiotropy among different types of brain-associated phenotypes. Further integrative analysis reveals putative causality routes among cell type-specific causal eGenes and brain-associated complex phenotypes. Finally, we characterize the spatiotemporal expression patterns of these causal eGenes, and highlight the coordinated associations of the brain-associated phenotypes based on the expression of their causal eGenes. Overall, our study presents a large-scale analysis of the genetic effects of brain structures, disorders and behaviors, providing a catalog of cell type-specific causal eGenes.

11.
arXiv (math.PR) 2026-06-25

Convergence Rates for Semistochastic Processes

arXiv:2606.25135v1 Announce Type: new Abstract: We study processes that consist of deterministic evolution punctuated at random times by disturbances with random severity; we call such processes semistochastic. Under appropriate assumptions such a process admits a unique stationary distribution. We develop a technique for establishing bounds on the rate at which the distribution of the random process approaches the stationary distribution. An important example of such a process is the dynamics of the carbon content of a forest whose deterministic growth is interrupted by natural disasters (fires, droughts, insect outbreaks, etc.).

12.
arXiv (quant-ph) 2026-06-11

Measurement incompatibility and quantum steering via linear programming

arXiv:2506.03045v3 Announce Type: replace Abstract: The problem of deciding whether a set of quantum measurements is jointly measurable is known to be equivalent to determining whether a quantum assemblage is unsteerable. This problem can be formulated as a semidefinite program (SDP). However, the number of variables and constraints in such a formulation grows exponentially with the number of measurements, rendering it intractable for large measurement sets. In this work, we circumvent this problem by transforming the SDP into a hierarchy of linear programs that compute upper and lower bounds on the incompatibility robustness with a complexity that grows polynomially in the number of measurements. The hierarchy is guaranteed to converge and it can be applied to arbitrary measurements – including non-projective POVMs (Positive Operator-Valued Measures) – in arbitrary dimensions. While convergence becomes impractical in high dimensions, in the case of qubits our method reliably provides accurate upper and lower bounds for the incompatibility robustness of sets with several hundred measurements in a short time using a standard laptop. We also apply our methods to qutrits, obtaining non-trivial upper and lower bounds in scenarios that are otherwise intractable using the standard SDP approach, although such bounds are significantly looser than the ones obtained in the qubit case. Finally, we show how our methods can be used to construct local hidden state models for states (i.e., to prove that a state cannot lead to steering under any possible local measurements), or conversely, to certify that a given state exhibits steering; for two-qubit quantum states, our approach is comparable to, and in some cases outperforms, the current best methods.

13.
arXiv (CS.CV) 2026-06-24

MapReason-OSM: Can Vision-Language Models Make Graph-Verifiable Mobility Decisions from Street Maps ?

Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable decision (a route, a pin, a parking choice) that must respect the road network. Yet most map benchmarks grade free text or multiple-choice answers that cannot be verified against the underlying graph. We present MapReason-OSM, a benchmark and evaluation harness for graph-verifiable mobility decisions on self-rendered OpenStreetMap panels. We render fixed-style maps for ten U.S. downtowns at two aligned zoom scales, overlay a consistent marker grammar, and pair each panel with a hidden street graph and exact oracles, yielding 6,000 instances (12,000 panels across the two zooms) over 12 routing, facility-location, and visual disambiguation tasks. Models return structured decisions that we snap back to the graph and score for validity, legality, optimality, and constraint satisfaction, plus cross-zoom consistency. Across seven VLMs, models read maps and route simply but fail at graph cost reasoning (single-facility pin placement is near chance even for frontier reasoning models), and are frequently scale-inconsistent. We release the benchmark, harness, and deterministic generator. Code and data: https://github.com/Vi-Sri/mapreason-osm

14.
arXiv (quant-ph) 2026-06-25

Preparing two-mode magnonic Schrödinger cat states in a cavity-magnon-qubit system

arXiv:2606.25511v1 Announce Type: new Abstract: The cavity-magnon-qubit system has recently been demonstrated as a new platform for preparing macroscopic quantum states in magnonic systems. Here, we propose to prepare a two-mode magnonic cat state, which is also a non-Gaussian entangled state, based on this practical system involving two yttrium-iron-garnet (YIG) spheres and a superconducting qubit coupled to a common microwave cavity. By adiabatically eliminating the cavity and resonantly driving the qubit, an effective magnon-qubit conditional-displacement interaction is achieved. Further working in the magnon-magnon strong-coupling regime and considering two identical magnon frequencies and coupling strengths to the cavity, two hybridized magnon modes are formed, of which the bright mode is prepared in a cat state after a projective measurement on the qubit, while the dark mode remains in its initial vacuum state. Such a state corresponds to a two-mode cat state of two original magnon modes, which share strong non-Gaussian entanglement. We also discuss practical dissipation and dephasing effects on the cat state. The results indicate that strong nonclassicality and non-Gaussian entanglement are present in the two-mode cat state using fully feasible parameters.

15.
medRxiv (Medicine) 2026-06-12

Disentangling Confounders from Pathology in Long-COVID Trajectory Prediction for Women: An Interpretable Large-Language-Model Approach

Objective. Post-acute sequelae of SARS-CoV-2 infection (PASC, "Long COVID") dispropor- tionately affects women, in whom hallmark symptoms–insomnia, fatigue, palpitations, cogni- tive difficulty–overlap with comorbidities and hormonal transitions such as menopause. This diagnostic overlap is a confounding problem: models that forecast future symptom severity risk attributing baseline physiological noise to viral pathology. We ask whether an interpretable, causally disentangled language model can separate true pathological signal from such con- founders while remaining competitive with strong predictors of future PASC severity

16.
arXiv (CS.CL) 2026-06-12

HyPE: Category-Aware Hypergraph Encoding with Persistent Edge Embeddings for Persona-Grounded Dialogue

Persona-grounded dialogue systems aim to produce responses consistent with a speaker's persona, yet existing methods treat personas as a flat set of sentences and fail to model the high-order relations among persona attributes-e.g., that several persona sentences share a topical category. We propose HyPE (Hypergraph Persona Encoder), a framework that (i) analyzes each persona-bearing text as a (Core, Expression, Sentiment, Category) quadruple, and (ii) organizes persona elements into a hypergraph whose hyperedges are induced by shared category labels. An HyperGCN hypergraph neural network propagates this structure into a persona summary vector and a soft-memory bank that condition the response generator. We further propose Persistent Edge Embeddings (PEE), lightweight per-category learnable priors fused into the HyperGCN message-passing step. On PersonaChat under greedy decoding, HyPE consistently outperforms sentence-level pooling baselines across GPT-2, LLaMA-3.2-3B, and Qwen2.5-3B backbones by demonstrating that structured hyperedge-level persona encoding provides a transferable advantage across model scales.

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

Cluster-Aware Dual-Level Test Specification Generation for Large-Scale Automotive Software Requirements

arXiv:2606.17197v1 Announce Type: cross Abstract: Generating test specifications that satisfy Automotive SPICE SWE.6 requirements becomes increasingly challenging and time-consuming as projects scale to thousands of requirements. Because this manual process often consumes weeks of engineering effort, automation becomes a critical necessity. However, standard Large Language Model (LLM) approaches struggle at scale: processing requirements individually discards vital inter-requirement dependencies, while feeding entire corpora at once exceeds context-window limits, leading to incomplete integration coverage and redundant test cases. This paper presents a novel "Cluster-then-Summarize" pipeline that addresses these limitations through three-stages. Requirements are embedded using sentence transformers and grouped using UMAP dimensionality reduction followed by HDBSCAN density-based clustering. This grouping utilizes an automatic minimum cluster size selection driven by a quality criterion combining normalized Silhouette and Calinski-Harabasz scores. A multi-level map-reduce summarization algorithm then distills each cluster into concise, domain-conformant descriptions while preserving quantitative thresholds and safety integrity levels. The pipeline exploits the derived cluster topology to generate test specifications at two levels: individual requirement verification and cluster-level integration tests that verify cross-requirement feature behavior. A nearby-cluster context mechanism provides bounded cross-feature awareness during each LLM call, and Retrieval-Augmented Generation grounds all outputs in ISO 26262 and ASPICE standards. Evaluation on automotive requirement datasets of varying scale demonstrates that the cluster-aware approach improves integration test coverage and maintains summarization fidelity compared to baseline methods while scaling efficiently to thousands of requirements.

18.
arXiv (quant-ph) 2026-06-11

Emergent mirror symmetry in the optimization of the central-spin quantum battery

arXiv:2606.11557v1 Announce Type: new Abstract: Quantum batteries provide a useful setting for exploring nonequilibrium many-body effects in energy storage. Here we investigate the optimization of a quantum battery based on the central-spin model. We identify two complementary structural indicators associated with the effective charging dynamics: one yields an upper bound on the average charging power, while the other characterizes the buildup of stored energy. We show that these two indicators are jointly optimized at a distinguished initial charger excitation number, which selects a particular Dicke sector of the model. At this common optimal point, the effective charging Hamiltonian becomes exactly mirror symmetric, suggesting mirror symmetry as a useful structural indicator for optimizing quantum batteries. We further show that the corresponding optimal dynamics can be closely approximated by product initial states, in particular by spin coherent states whose excitation-number distribution is centered at the symmetry-selected point. Our results establish a direct connection between charging performance, optimal-state structure, and emergent symmetry in the central-spin quantum battery, and suggest symmetry as a useful organizing principle for efficient charging in interacting many-body quantum systems.

19.
arXiv (CS.CV) 2026-06-25

Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis

Accurate classification of diffuse gliomas is often hindered by domain shifts across centers and a lack of large, annotated datasets. We propose the Anatomically-conditioned Latent Diffusion Model (ALDM), a novel framework for data-efficient, few-shot 3D volumetric MRI synthesis. ALDM utilizes a two-stage approach: a 3D variational autoencoder learns anatomical priors from a data-rich source domain, while a conditional latent diffusion model, guided by tumor masks via a ControlNet, generates structurally coherent volumes for a data-scarce target domain. Evaluated in an extreme few-shot setting with only 16 target images, ALDM outperformed GAN and hybrid baselines, achieving a superior Frechet Inception Distance (FID) of 85.40 and a downstream classification AUC of 0.987. Qualitative results confirm that the model preserves sharp pathology boundaries and cross-modal consistency, with visual fidelity improving progressively during training. By capturing essential diagnostic features, ALDM provides a robust tool for clinical data augmentation in low-resource settings. Our implementation is available at https://github.com/Analytics-Everywhere-Lab/anatomically-conditioned-LDM.

21.
arXiv (CS.CV) 2026-06-17

TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all stages: collecting and labeling millions of driving frames is costly, and closed-loop RL on images is bottlenecked by the per-step cost of photorealistic rendering plus a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: millions of rollout steps per second, and a state distribution naturally rich in collisions, near-misses, and recoveries that no driving log contains. Our approach exploits this asymmetry by decoupling learning to drive from learning to see. We pretrain a single policy by self-play, then align its latent space with a pretrained vision backbone, through the action KL divergence and a batch-relational low-rank structural loss. The action target comes from the self-play policy, so alignment never supervises against a logged trajectory: a paired dataset of (image, scene-state) frames suffices, with no need for the curated expert demonstrations that imitation pretraining is built on. On photorealistic 3D Gaussian splatting closed-loop scenarios, the resulting end-to-end policy matches or exceeds prior end-to-end methods.

22.
medRxiv (Medicine) 2026-06-24

Epidural versus Transcutaneous Spinal Cord Stimulation for Motor Recovery after Spinal Cord Injury: A Comparative Analysis

Spinal cord injury (SCI) is a devastating neurological injury that results in the profound loss of voluntary motor function and marked reduction in quality of life. Rehabilitation remains as the standard of care for recovery after SCI; however, it often falls short in recovering meaningful motor function. Spinal cord stimulation (SCS) has emerged as a promising neurostimulation approach to fill this gap and recover lost voluntary motor function. Two main approaches of SCS have been designed and implemented for human use: epidural and transcutaneous SCS. Over the last two decades, several clinical studies have shown convincing evidence that both epidural and transcutaneous SCS can be used in conjunction with rehabilitation to improve motor function of individuals after SCI. Yet fundamental clinical questions remain unanswered: when should clinicians choose epidural or transcutaneous SCS, which technique provides the most durable outcomes, and for whom is each therapy best? Without these answers, widespread and meaningful adoption of either approach into clinical practice will remain limited. To address these questions, in this Review, we define the distinct therapeutic goals, intended use cases, clinical parameters, and responder profiles for both epidural and transcutaneous SCS to guide their eventual adoption into clinical practice. We found that indeed epidural and transcutaneous SCS serve distinct therapeutic roles. Epidural SCS is designed as an assistive therapy that can restore muscle activity and single joint movements immediately within one week of implantation, while transcutaneous SCS is designed as a long-term therapeutic device with cumulative functional gains observed over treatment periods of up to 18 weeks. Lastly, epidural SCS produced benefits for all participants (AIS A-D) despite the extent of their injury, while transcutaneous SCS only consistently benefits individuals with incomplete motor injuries (AIS C-D).

23.
medRxiv (Medicine) 2026-06-24

An Automated, Pathologist-free Gleason Grade Stratifies Disease-free Interval Comparably to Expert Grading from a Single Out-of-distribution Slide

Automated Gleason grading now matches expert pathologists on the cohorts where systems are developed and tuned, but deployment-relevant gaps remain: whether an automated grade, applied without site-specific tuning or pathologist oversight, stratifies outcome comparably to expert grading on slides from unseen institutions and in cross-specimen applications. We tested this for disease-free interval (DFI), a curated recurrence endpoint. A production gland-level prostate diagnostic (PathTools Prostate v11.0) was applied frozen and uncalibrated to 298 diagnostic whole-slide images from 274 TCGA-PRAD radical-prostatectomy patients, a cohort outside its development distribution and needle-core-biopsy training data, contributed by 25 source sites under heterogeneous digitization; tissue was detected automatically with no expert region annotation. From the output we derived an ISUP grade group and continuous high-grade content, and evaluated each grade as a standalone predictor of DFI (24 events) by Harrell's c-index with 95% bootstrap confidence intervals, a paired between-method bootstrap, and Kaplan-Meier curves with the log-rank test. The automated grade reproduced the clinical grade group at quadratic-weighted kappa = 0.62 (95% CI 0.53-0.70; 48% exact, 86% within one group), within the expert inter-observer range. As the sole predictor it stratified recurrence (log-rank p = 0.022; c-index 0.69, 95% CI 0.58-0.79), and the continuous high-grade fraction was robustly prognostic (hazard ratio 1.37 per SD, p = 0.029; c-index 0.71, 0.61-0.81). Standalone discrimination was not statistically separable from the clinical grade (c-index 0.78, 0.69-0.86; paired {triangleup} c-index spanning zero), and in a joint model the automated grade added nothing beyond it, consistent with both measuring a shared morphological axis. From a single out-of-distribution slide with no pathologist oversight, the automated grade provides standalone recurrence stratification not statistically separable from whole-gland expert grading, demonstrating robust generalizability beyond training data; reported as a continuous high-grade fraction, it offers reproducible, expert-free, grade-equivalent risk stratification for harmonizing large archival or genomically-profiled cohorts.

24.
arXiv (CS.CV) 2026-06-24

Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent

Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image Clustering Agent, the first universal framework that bridges these gaps through textual guidelines. To incorporate complex guidelines without task-specific training, we propose Generative Concept Proxy Modeling, which generates guideline-aware embeddings via concept proxy extraction. For scenarios requiring automatic cluster discovery, we introduce LLM Traversal based on Minimum Spanning Tree that selectively applies LLM reasoning for complex semantic judgments. Our method generalizes across diverse clustering scenarios spanning from general to fine-grained categorization, from global to local criteria, and from balanced to long-tail distributions. Our framework consistently outperforms specialized methods across diverse clustering tasks.

25.
arXiv (CS.AI) 2026-06-24

Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System

arXiv:2606.24839v1 Announce Type: new Abstract: Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics. This makes them more challenging to evaluate than single-turn LLM responses. It is therefore necessary to distinguish genuine disagreement between an agent's output and a ground-truth answer from grading artifacts. We investigate how reliably automated graders assess such a system and what strategies improve grading quality by applying LAMBDA, a multi-agent data-analysis system, on 153 numerical QRData tasks from DSGym. We develop and evaluate a three-layer human-AI grading cascade: strict regex matching, LLM-based lenient grading, and snippet-based human inspection, which combines non-GenAI and GenAI strategies with different failure profiles. Both automated graders achieve 100% observed precision (0/70 false positives). The lenient grader's recall is 97% against human labels. A keyword-anchored extraction pipeline raises the strict grader's recall by 60 percentage points over a last-number heuristic; the lenient grader is architecturally parser-independent. An iterative nudge mechanism raises grading run success from 36% to 97% and lenient-pass rates from 16% to 46%; comparing nudging with and without original-question re-injection shows that re-injection offers no benefit, confirming the nudge as an answer template cue. We further observe in this case study that variable type is the task metadata field most consistently associated with grading pipeline dynamics and observed outcome grades.