Explore the Frontier of Global Academia

01.

medRxiv (Medicine) 2026-06-22 DOI: HASH:04ed6cdb383bd67a060af68674fb4810

Agentic Artificial Intelligence for Hospital Readmission Review: A Single-Center Blinded Evaluation and Exploratory Qualitative Analysis

Authors:

Gensheimer↗M. F↗Adhikari↗Parmer-Chow↗Liu↗Ma↗Shieh↗

Background: Manual review of 30-day hospital readmissions can identify actionable quality and safety problems, but it is labor-intensive. We developed and evaluated an agentic AI workflow for evidence-grounded readmission review. Materials and methods: We studied adult patients with unplanned 30-day readmission after discharge from a medicine hospitalist service at a single academic health system. An AI agent using a large language model queried a database containing notes, encounters, procedures, laboratory results, and other clinical data, and completed the same structured readmission-review rubric used by physicians. In the primary comparative evaluation, 20 randomly selected readmissions from 2025 were each reviewed by two physicians and the AI system. Blinded physician evaluators rated review quality. After rubric refinement, the AI workflow was applied to 100 recent readmissions in an exploratory expanded-cohort analysis of recurring improvement opportunities. Results: In the primary comparative evaluation, the AI classified 9/20 readmissions (45%) as preventable, compared with 19/40 physician reviews (47.5%). Blinded overall quality ratings were similar for AI and physician reviews (4.35 vs. 4.20 on a 1-5 scale; mean difference 0.15, 95% CI -0.20 to 0.48; p=0.49), as were factuality/support and usefulness/actionability ratings. No AI hallucinations were identified during factuality review. Agreement on preventability and primary readmission category was low for both AI-human and human-human comparisons. The AI system cost $0.23 per chart; physician reviewers took a median of 15 minutes, corresponding to an estimated $42.43 per chart. In the exploratory expanded-cohort analysis, AI-assisted review identified recurring vulnerabilities in post-discharge follow-up plans, incomplete inpatient workups, medication-safety transitions, and indwelling-device transitions. Conclusions: Agentic AI produced readmission reviews with similar blinded quality ratings to physician reviews in this small single-center primary comparative evaluation and supported identification of recurring quality-improvement themes in the exploratory expanded-cohort analysis. Preventability judgments remained variable among both AI and physicians, underscoring the need for human oversight and prospective evaluation before operational use.

Read & Discuss → View Source →

02.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2605.26759

Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining

Authors:

Biao Ouyang↗Tengxue Zhang↗Zhihao Zhuang↗Yang Shu↗Chenjuan Guo↗Bin Yang↗

arXiv:2605.26759v2 Announce Type: replace Abstract: Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their causal discovery capabilities to new time series governed by diverse causal mechanisms. In this paper, we propose PTCD, a novel Pretraining framework for Time-series Causal Discovery, which improves cross-task generalization through context-conditioned modeling and transferable causal augmentation. To model complex temporal causal dependencies, PTCD employs a dual-scale iterative attention mechanism to capture window-level causal relationships, and a Gaussian mixture with a context-level routing mechanism to handle heterogeneous exogenous distributions. To further address distribution shifts across causal graphs, PTCD adopts a pretraining paradigm on synthetic datasets that integrates intervention-based learning and a causal mixup strategy, promoting stable causal discovery and stronger generalization. Extensive experiments on multiple real-world out-of-distribution (OOD) datasets demonstrate that PTCD excels in both causal discovery and root cause identification.

Read & Discuss → View Source →

03.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2604.03472

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

Authors:

Jacob Dineen↗Aswin RRV↗Zhikun Xu↗Ben Zhou↗

Co-evolutionary self-play, where one language model generates problems and another solves them, promises autonomous curriculum learning without human supervision. In practice, the proposer quickly converges to a narrow distribution of problems that satisfy the reward function. This diversity collapse renders the curriculum uninformative for the solver, stalling the co-evolutionary loop. We introduce vocabulary dropout, a random mask applied to the proposer's output logits during both policy training and curriculum generation, as a lightweight mechanism to sustain diversity. The mask is hard and non-stationary, preventing the proposer from locking into fixed token sequences. Training Qwen3-4B and Qwen3-8B on mathematical reasoning via R-Zero, we find that vocabulary dropout sustains proposer diversity across lexical, semantic, and functional metrics throughout training. It also yields solver improvements averaging +4.4 points at 8B, with the largest gains on competition-level benchmarks. Our findings suggest that explicit action-space constraints, analogous to the structural role that game rules play in classical self-play, can help sustain productive co-evolution in language. Vocabulary dropout is one simple instantiation of this principle.

Read & Discuss → View Source →

04.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19108

JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling

Authors:

Daochen Zha↗Chun How Tan↗Xin Liu↗Bin Xu↗Han Zhao↗Xiaowei Liu↗Tracy Yu↗Hui Gao↗Huiji Gao↗Liwei He↗Stephanie Moyerman↗Sanjeev Katariya↗…

arXiv:2606.19108v1 Announce Type: new Abstract: Sequence modeling has become increasingly popular in recommendation and ranking algorithms, owing to its capacity to model users' historical behaviors and infer user intentions. Despite its theoretical simplicity, the practical deployment of a sequence model in production is non-trivial due to complexity of the sequence and sparse labels. For example, in Airbnb, guest sequences are often long, exploratory and complex, and we focus on booking labels, which are sparse. As such, we are often required to make various design decisions regarding data and modeling to strike a balance between effectiveness and scalability. This work delved into these production challenges and deployed JourneyFormer, a sequence modeling solution for search ranking at Airbnb. We detail crucial design considerations, covering aspects such as guest event selection, ID embeddings, model architecture, and label attribution. Additionally, we describe several tailored strategies to accelerate model training and inference. JourneyFormer has been successfully deployed within Airbnb's production, where its effectiveness and impact have been evidenced not only by improved offline ranking metrics but also by significant gains in key business metrics through online A/B testing across 2 production surfaces.

Read & Discuss → View Source →

05.

Nature (Science) 2026-06-09 DOI: HASH:7563684b41492cac9361df955542091d

People are turning to AI chatbots to plug gaps in health information

Authors:

Moritz Gerstung↗

A systematic assessment of health-related queries to a chatbot powered by artificial intelligence highlights shortfalls in health-care provision and the responsibilities of AI companies. A systematic assessment of health-related queries to a chatbot powered by artificial intelligence highlights shortfalls in health-care provision and the responsibilities of AI companies.

Read & Discuss → View Source →

06.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18954

GraphPO: Graph-based Policy Optimization for Reasoning Models

Authors:

Yuliang Zhan↗Xinyu Tang↗Jian Li↗Dandan Zheng↗Weilong Chai↗Jingdong Chen↗Jun Zhou↗Ge Wu↗Wenyue Tang↗Hao Sun↗

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for enhancing the capability of large reasoning models. RLVR typically samples responses independently and optimizes the policy using from final answers. This paradigm has two limitations. First, independently responses often contain similar intermediate reasoning steps, causing redundant exploration and wasted computation. Second, sparse final-answer rewards make it hard to identify useful steps. Tree-based methods partly address this problem by sharing prefixes and comparing branches from the same prefix to provide fine-grained signals. However, tree branches are still expanded independently. When different branches reach similar reasoning states, they cannot share information and repeat similar exploration. Moreover, tree-based methods ignore such dispersion and only perform local comparisons within separate branches, which can lead to higher variance in advantage estimation. To address this challenge, we propose GraphPO (Graph-based Policy Optimization), a novel RL framework that represents rollouts as a directed acyclic graph, with reasoning steps as edges and semantic states summarized from the reasoning paths as nodes. GraphPO merges semantically equivalent reasoning paths into equivalence classes, allowing them to share suffixes and reallocating budget away from redundant expansions to diverse exploration. Furthermore, we assign efficiency advantages to incoming edges and correctness advantages to outgoing edges, thereby improving inference efficiency while deriving process supervision from outcome. Theory shows that GraphPO reduces advantage-estimation variance and enhances reasoning efficiency. Experiments on three LLMs across reasoning and agentic search benchmarks show that GraphPO consistently outperforms chain- and tree-based baselines with the same token budgets or response budgets.

Read & Discuss → View Source →

07.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2602.10384

When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents

Authors:

Virginie Mouilleron↗Th\'eo Lasnier↗Anna Mosolova↗Djam\'e Seddah↗

Vision-language models (VLMs) perform well on many document understanding tasks, yet their reliability in specialized, non-English domains remains underexplored. This gap is especially critical in finance, where documents mix dense regulatory text, numerical tables, and visual charts, and where extraction errors can have real-world consequences. We introduce Scribe Finance, the first multimodal benchmark for evaluating French financial document understanding. The dataset contains 1,204 expert-validated questions spanning text extraction, table comprehension, chart interpretation, and multi-turn conversational reasoning, drawn from real investment prospectuses, KIDs, and PRIIPs. We evaluate six open-weight VLMs (8B-124B parameters) using an LLM-as-judge protocol. While models achieve strong performance on text and table tasks (85-90% accuracy), they struggle with chart interpretation (34-62%). Most notably, multi-turn dialogue reveals a sharp failure mode: early mistakes propagate across turns, driving accuracy down to roughly 50% regardless of model size. These results show that current VLMs are effective for well-defined extraction tasks but remain brittle in interactive, multi-step financial analysis. Scribe Finance offers a challenging benchmark to measure and drive progress in this high-stakes setting.

Read & Discuss → View Source →

08.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.11759

Random Grover Search

Authors:

Dekuan Dong↗Jiaxin Ma↗Yingzhou Li↗

arXiv:2606.11759v1 Announce Type: new Abstract: Grover's algorithm achieves a quadratic speedup for unstructured search given a global oracle for the target set. In many applications, however, the target set is specified as the intersection of multiple constraint sets. Constructing a global oracle for the intersection can be costly, whereas the individual constraint oracles are often much simpler to implement. We study a randomized Grover search algorithm that directly uses these constraint oracles. At each iteration, one of the corresponding Grover operators is selected at random. For the two-operator case with uniform sampling, we prove that the success probability approaches one after \[ \Theta \left(\frac\pi4\sqrt{\frac{N}{r}}\right) \] iterations, where $r$ is the size of the intersection. Thus, the algorithm achieves the same asymptotic query complexity as standard Grover search but without requiring a global oracle. We then generalize the analysis to arbitrary sampling distributions and an arbitrary number of Grover operators through an auxiliary operator that approximates the expected Grover evolution, while retaining the same asymptotic complexity. We further show that highly biased sampling distributions can still achieve near-unit success probability, enabling cheaper Grover operators to be used more frequently. Finally, we prove asymptotic optimality and support the theoretical results with numerical simulations.

Read & Discuss → View Source →

09.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2509.24894

Improved Stochastic Optimization of LogSumExp

Authors:

Egor Gladin↗Alexey Kroshnin↗Jia-Jie Zhu↗Pavel Dvurechensky↗

arXiv:2509.24894v4 Announce Type: replace-cross Abstract: The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In practice, when the number of exponential terms inside the logarithm is large or infinite, optimization becomes challenging since computing the gradient requires differentiating every term. We propose a novel convexity- and smoothness-preserving approximation to LogSumExp that can be efficiently optimized using stochastic gradient methods. This approximation is rooted in a sound modification of the KL divergence in the dual, resulting in a new $f$-divergence called the Safe KL divergence. Our experiments and theoretical analysis of the LogSumExp-based stochastic optimization, arising in DRO and continuous OT, demonstrate the advantages of our approach over existing baselines.

Read & Discuss → View Source →

10.

medRxiv (Medicine) 2026-06-17 DOI: HASH:e82035d687f1ae641209a75445536f9d

What Urine Measures Is Not What Tissue Encodes: Compartment-Specific miRNA Coordination in Prostate Cancer

Authors:

Singh↗Biswas↗Jain↗Trivedi↗Yadav↗Gupta↗Kumar↗Das↗

Abstract Background Prostate cancer (PCa) diagnosis remains challenged by the limited specificity of prostate-specific antigen (PSA) testing, which cannot reliably distinguish malignancy from benign prostatic hyperplasia (BPH). MicroRNAs (miRNAs) are emerging candidates for liquid biopsy-based diagnostics, but most studies assess expression in isolation within a single compartment (biological source - Tissue, blood, serum, urine etc.), overlooking both compartment-specific behavior and the coordinated relationships among miRNAs. Methods We profiled four candidate miRNAs — miR-19b-3p, miR-21-5p, miR-101-3p and miR-375-3p, across four biological compartments (prostate tumor tissue, urine, serum, and blood) in 179 patients undergoing prostate biopsy for clinical suspicion of PCa (104 PCa, 75 BPH) using qRT-PCR. Urinary exosomal RNA was isolated with a commercial exosome isolation kit so from here onwards this compartment will be referred to as urine. Differential expression was quantified using Cohen's d; inter-miRNA coordination was assessed via Spearman correlation and differential correlation ({delta} r) analysis; and a compartment-level network rewiring score was derived as the sum of {delta} r| across miRNA pairs. Cross-compartment structural alignment was evaluated by comparing correlation patterns at the population level. Diagnostic models combining PSA, age, and urinary exosomal-miRNA features were evaluated using Logistic Regression, Elastic Net Logistic Regression and Naive Bayes classifiers under leave-one-out cross-validation (LOOCV). Results Effect sizes were largest and most consistent in urine, with miR-101-3p showing the strongest separation between PCa and BPH (d = -1.01), followed by miR-21-5p (d {approx}-0.72$) and miR-19b-3p (d {approx}-0.64). Two markers (miR-19b-3p, miR-375-3p) showed directional reversals across compartments, indicating that disease-associated signals are compartment-specific rather than uniformly conserved. In tumor tissue, PCa was associated with substantial reorganization of inter-miRNA coordination (network rewiring score = 2.46), including the emergence of a strong miR-21-5p–miR-375-3p co-regulatory axis ({delta} r = +0.87$) and decoupling of the miR-21-5p–miR-19b-3p relationship ({delta}r = -0.64$). Urine showed a structurally distinct coordination pattern (rewiring score = 1.77), dominated by a miR-101-3p–miR-19b-3p axis (r = +0.56) absent from tissue; cross-compartment comparison showed concordance in only 1 of 5 miRNA pairs, indicating that urine's architecture is largely independent of tissue's. For diagnostic translation, the conventional PSA cutoff (4 ng/mL) achieved 100% sensitivity but only 23.5% specificity. In urine, miR-101-3p performs better than other miRNAs, with AUC of 0.77 (95% CI: 0.62–0.90). Adding PSA and age to the urinary miR-101-3p further improved discrimination to an AUC of 0.91 (95% CI: 0.82–0.99), with 70% specificity at 92% sensitivity; this pattern was consistent across Elastic Net and Logistic Regression classifiers. Expanding the model to include all urinary miRNAs, age, and pair-derived coordination features did not improve on this result (AUC = 0.88), indicating that population-level coordination changes did not translate into additional individual-level diagnostic value in this cohort. Conclusions miRNA signals in extracellular compartments do not represent direct surrogates of tumor-level molecular architecture; each compartment harbors a distinct, transformed coordination structure reflecting its biological context. While these coordination-level changes are mechanistically informative, the most direct translational gain in this study came from a parsimonious model combining PSA, age with a single urinary marker, miR-101-3p, which improved AUC from 0.77 to 0.91, with specificity 70.5% at 90% sensitivity criteria. This combination represents a promising, interpretable candidate for reducing unnecessary prostate biopsies, pending validation in larger, independent cohorts. Keywords: MicroRNA, Compartment-Specific Biomarkers, Urinary Exosomes, Differential Correlation, Liquid Biopsy, Machine learning, PSA, Early diagnosis

Read & Discuss → View Source →

11.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18993

Sequential Kernel-based Conditional Independence Testing via Adaptive Betting

Authors:

Zheng He↗Danica J. Sutherland↗

arXiv:2606.18993v1 Announce Type: cross Abstract: Testing conditional independence is fundamental yet intrinsically difficult: without additional assumptions, Type I error control is impossible in general. The "Model-X'' paradigm addresses this difficulty by assuming exact knowledge of a relevant conditional distribution. While small deviations from this assumption can sometimes be tolerated in classical one-shot testing, existing sequential conditional independence tests typically require the Model-X conditional to be known exactly, making them fragile when it must instead be estimated. We propose a new approach that is substantially more robust to such estimation error. Our method applies testing-by-betting to an adaptively optimized Kernel Conditional Independence statistic, together with a normalization scheme and a truncate-and-shift calibration strategy. These modifications greatly reduce Type I error inflation while preserving high power across high-dimensional synthetic benchmarks and real-world fairness tasks, outperforming existing sequential Model-X approaches. Code is available at https://github.com/he-zh/SKCI.

Read & Discuss → View Source →

12.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2510.10981

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning

Authors:

Tomoya Wakayama↗Taiji Suzuki↗

arXiv:2510.10981v3 Announce Type: replace-cross Abstract: This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We introduce a principled risk decomposition that separates the total ICL risk into two orthogonal components: Bayes Gap and Posterior Variance. The Bayes Gap quantifies how well the trained model approximates the Bayes-optimal in-context predictor. For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts and their context length. The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty. Our key finding is that this term is determined solely by the difficulty of the true underlying task, while the uncertainty arising from the task mixture vanishes exponentially fast with only a few in-context examples. Together, these results provide a unified view of ICL: the Transformer selects the optimal meta-algorithm during pretraining and rapidly converges to the optimal algorithm for the true task at test time.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.04145

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

Authors:

Guilin Zhang↗Chuanyi Sun↗Shahryar Sarkani↗John M. Fossaceca↗

arXiv:2606.04145v2 Announce Type: replace-cross Abstract: Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality. As Gao et al. (2023) showed, this proxy diverges from world feedback (downstream eval metrics) under sustained optimization pressure, a phenomenon known as reward overoptimization. Existing platform schedulers ignore this divergence: non-clairvoyant schedulers optimize JCT without any quality signal, SLAQ-style quality-aware schedulers use training loss (a weaker proxy that drops monotonically through hacking), and classical per-job early stopping requires human monitoring and does not free shared GPUs. We propose EvalStop, a composable scheduling primitive that terminates jobs on k consecutive eval-score declines, releases GPUs, preserves the best checkpoint, and delegates to any base scheduler. We frame scheduler-level early stopping as a detection problem and evaluate it in a discrete-event simulator whose RLHF workload mixes reward-hacking and structurally healthy runs, with ground-truth labels hidden from schedulers. On RLHF-heavy workloads (80% RLHF, 64 GPUs), EvalStop achieves precision 98% / recall 99% / FPR 1.5% while improving JCT by 9% and cutting wasted compute by 22% over SRTF-Est (p

Read & Discuss → View Source →

14.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16721

Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies

Authors:

Ke Liu↗Mengxuan Li↗Yanyi Bao↗Tianyun Zhang↗Chong Chu↗Jiajun Bu↗Haishuai Wang↗

arXiv:2606.16721v1 Announce Type: new Abstract: Medical diagnosis and treatment are dynamic processes in which patient states evolve over time and clinical interventions alter future outcomes. Although current medical AI can detect disease, estimate risk and generate reports, many systems still return static labels or scores, offering limited insight into how illness may progress or how alternative interventions may reshape its trajectory. Medical world models adapt the world-model idea from artificial intelligence to healthcare by learning internal simulators of patient-state dynamics. Their long-term goal is to help clinicians anticipate deterioration, compare treatment-conditioned futures and tailor care to individual patients. Yet relevant work remains scattered across foundation models, longitudinal modelling, disease simulation, treatment-effect estimation, reinforcement learning and digital twins. To bridge this gap, this review outlines a roadmap for advancing medical AI from isolated diagnosis and prediction toward medical world models that simulate disease evolution and support intervention decisions. This roadmap is organized around three coupled capabilities: patient-state construction, clinical dynamics modelling and intervention decision support. Across representative systems, the comparison highlights what each capability contributes and how partial components can be integrated into more mature perception–dynamics–planning systems. Finally, we identify the challenges involved in turning plausible rollouts into clinically useful simulators. Related literature is available at https://github.com/1999kevin/awesome_medical_world_models.

Read & Discuss → View Source →

15.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2602.23116

Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

Authors:

Junghyun Lee↗Minju Hong↗Kwang-Sung Jun↗Chulhee Yun↗Se-Young Yun↗

arXiv:2602.23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback. While various regularizers are utilized to robustify alignment, known polylogarithmic regret guarantees remain heavily specific to KL. To investigate whether such fast rates extend beyond KL, we adopt the Generalized Bilinear Preference Model (GBPM) – capturing intransitive preferences over $d$-dimensional item-wise features via a rank-$2r$ skew-symmetric matrix – to isolate the impact of generic regularization. Crucially, under GBPM, we prove that the dual gap of any greedy policy is bounded by the squared estimation error, derived using only strong convexity and skew-symmetry. Under a feature coverage assumption, we establish a generic polylogarithmic regret of $\tilde{\mathcal{O}}(\eta d^4 C_{\min}^{-1} (\log T)^2 \wedge d^2 C_{\min}^{-1/2} \sqrt{T})$ with Greedy Sampling, and a dimension-wise improved regret (for well-conditioned arm-sets) of $\tilde{\mathcal{O}}(C_{\min}^{-2} \sqrt{\eta r T} \wedge r^{1/3} C_{\min}^{-4/3} T^{2/3})$ with Explore-Then-Commit, where $\eta^{-1}$ is the regularization coefficient, $T$ is the time horizon, and $C_{\min}$ is an arm-set dependent quantity. This demonstrates that ``fast'' regrets are not KL-specific, but rather a fundamental consequence of generic strongly convex geometry.

Read & Discuss → View Source →

16.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2412.15557

MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems

Authors:

Aaron Guoxiang Guo↗Aldeida Aleti↗Neelofar Neelofar↗Chakkrit Tantithamthavorn↗Yuanyuan Qi↗Tsong Yueh Chen↗

With the widespread application of LLM-based dialogue systems in daily life, quality assurance has become more important than ever. Recent research has successfully introduced methods to identify unexpected behaviour in single-turn testing scenarios. However, multi-turn interaction is the common real-world usage of dialogue systems, yet testing methods for such interactions remain underexplored. This is largely due to the oracle problem in multi-turn testing, which continues to pose a significant challenge for dialogue system developers and researchers. In this paper, we propose MORTAR, a metamorphic multi-turn dialogue testing approach, which mitigates the test oracle problem in testing LLM-based dialogue systems. MORTAR formalises the multi-turn testing for dialogue systems, and automates the generation of question-answer dialogue test cases with multiple dialogue-level perturbations and metamorphic relations (MRs). The automated MR matching mechanism allows MORTAR more flexibility and efficiency in metamorphic testing. The proposed approach is fully automated without reliance on LLM judges. In testing six popular LLM-based dialogue systems, MORTAR reaches significantly better effectiveness with over 150\% more bugs revealed per test case when compared to the single-turn metamorphic testing baseline. Regarding the quality of bugs, MORTAR reveals higher-quality bugs in terms of diversity, precision and uniqueness. MORTAR is expected to inspire more multi-turn testing approaches, and assist developers in evaluating the dialogue system performance more comprehensively with constrained test resources and budget.

Read & Discuss → View Source →

17.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2601.03112

DiT-JSCC: Rethinking Deep JSCC with Diffusion Transformers and Semantic Representations

Authors:

Kailin Tan↗Jincheng Dai↗Sixian Wang↗Guo Lu↗Shuo Shao↗Kai Niu↗Wenjun Zhang↗Ping Zhang↗

Generative joint source-channel coding (GJSCC) has emerged as a new Deep JSCC paradigm for achieving high-fidelity and robust image transmission under extreme wireless channel conditions, such as ultra-low bandwidth and low signal-to-noise ratio. Recent studies commonly adopt diffusion models as generative decoders, but they frequently produce visually realistic results with limited semantic consistency. This limitation stems from a fundamental mismatch between reconstruction-oriented JSCC encoders and generative decoders, as the former lack explicit semantic discriminability and fail to provide reliable conditional cues. In this paper, we propose DiT-JSCC, a novel GJSCC backbone that can jointly learn a semantics-prioritized representation encoder and a diffusion transformer (DiT) based generative decoder, our open-source project aims to promote the future research in GJSCC. Specifically, we design a semantics-detail dual-branch encoder that aligns naturally with a coarse-to-fine conditional DiT decoder, prioritizing semantic consistency under extreme channel conditions. Moreover, a training-free adaptive bandwidth allocation strategy inspired by Kolmogorov complexity is introduced to further improve the transmission efficiency, thereby indeed redefining the notion of information value in the era of generative decoding. Extensive experiments demonstrate that DiT-JSCC consistently outperforms existing JSCC methods in both semantic consistency and visual quality, particularly in extreme regimes.

Read & Discuss → View Source →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.09163

FORTIS: Benchmarking Over-Privilege in Agent Skills

Authors:

Shawn Li↗Chenxiao Yu↗Han Wang↗Wei Yang↗Ryan Rossi↗Franck Dernoncourt↗Xiyang Hu↗Philip Yu↗Chaowei Xiao↗Huan Zhang↗Yue Zhao↗

arXiv:2605.09163v3 Announce Type: replace Abstract: Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a privilege boundary that current models routinely exceed. We present FORTIS, a benchmark that evaluates over-privilege in agent skills across two stages: whether a model selects the minimally sufficient skill from a large overlapping library, and whether it executes that skill without expanding into broader tools or actions than the skill permits. Across ten frontier models and three domains, we find that over-privileged behavior is the norm rather than the exception. Models consistently reach for higher-privilege skills and tools than the task requires, failing at both stages at rates that remain high even for the strongest available models. Failure is especially severe under the ordinary conditions of real user interaction: incomplete specification, convenience framing, and proximity to skill boundaries. None of these requires adversarial construction. The results indicate that the skill layer, far from containing agent behavior, is itself a primary source of privilege escalation in current systems.

Read & Discuss → View Source →

19.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2510.03896

GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert

Authors:

Mingyu Liu↗Zheng Huang↗Xiaoyi Lin↗Muzhi Zhu↗Canyu Zhao↗Yating Wang↗Haoyi Zhu↗Hao Chen↗Chunhua Shen↗

Vision-language models demonstrate strong reasoning and planning abilities, yet grounding these predictions into precise robot actions remains a central challenge. Existing Vision-Language-Action methods typically entangle reasoning and action generation, leading to limited generalization. We propose Generalizable Action Expert (GAE), a task-agnostic model that converts sparse geometric plans into dense robot actions. Our approach introduces a sparse geometric interface: the VLM predicts sparse 3D waypoints representing high-level intention, while GAE maps these waypoints together with real-time point cloud observations to continuous action trajectories. GAE is pretrained on a large-scale pointcloud-trajectory dataset comprising 150k trajectories from both simulation and real-world robots. To further improve efficiency and generalization, we introduce an Action Pre-training, Pointcloud Fine-tuning (APPF) scheme that decouples learning action dynamics from geometry grounding. After pretraining, GAE is frozen and reused across downstream tasks, requiring only lightweight fine-tuning of the VLM to produce the sparse interface. Experiments show that our method achieves strong performance and generalization across diverse visual domains, camera viewpoints, and natural language instructions.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2603.00026

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents

Authors:

Xiaohui Zhang↗Zequn Sun↗Chengyuan Yang↗Yaqin Jin↗Yazhong Zhang↗Wei Hu↗

Memory management is essential for LLM agents in long-term interactions. Current memory frameworks typically treat agents as passive ``recorders'' and retrieve information without understanding its deeper implications. They may fail in scenarios requiring reasoning and complex decision-making. To bridge this critical gap, we propose a novel actionable memory framework called ActMem that integrates memory retrieval with active causal reasoning. ActMem transforms unstructured dialogue history into a structured causal and semantic graph. By leveraging counterfactual reasoning and commonsense completion, it enables agents to deduce implicit constraints and resolve potential conflicts between past states and current intentions. Furthermore, we introduce a comprehensive dataset ActMemEval to evaluate agent reasoning capabilities in logic-driven scenarios, moving beyond the fact-retrieval focus of existing memory benchmarks. Experiments demonstrate that ActMem significantly outperforms baselines in handling complex, memory-dependent tasks, paving the way for more consistent and reliable intelligent assistants.

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15743

Unsupervised Learning for Missing Modalities in Multimodal Learning

Authors:

Hassan Ismkhan↗Hamid Bouchahcia↗

arXiv:2606.15743v1 Announce Type: new Abstract: This paper addresses the missing-modality challenge in multi-modal learning by introducing Unsupervised Learning for Missing Modalities in Multi-Modal Learning (UL4M4), a flexible framework that imputes missing feature embeddings in a task-independent manner before supervised prediction. We propose modality-specific normalization and a novel partial-modality distance metric to enable fair clustering of incomplete observations, capturing cross-modal structures while preserving scale-invariance across varying dimensionalities and modality counts. Cluster centers from this unsupervised stage guide an iterative greedy imputation process for any missing modalities during training or inference, supporting arbitrary numbers of modalities and arbitrary missing patterns per sample. The imputation module is lightweight, uses frozen encoders, and decouples from the downstream task, allowing easy integration with any fusion/prediction architecture. Extensive experiments under diverse and highly incomplete regimes demonstrate UL4M4's robustness, achieving, to the best of our knowledge, the first consistent F1-Micro scores above 0.7 on challenging missing configurations even when more than 50\% of modality slots are missing. Results are also stable across cluster sizes and significantly outperform state-of-the-art baselines. Code is available here: https://github.com/h-ismkhan/Multimodal-Learning-with-Missing-Modalities-via-Unsupervised-Learning.

Read & Discuss → View Source →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2508.04243

Automated ultrasound doppler angle estimation using deep learning

Authors:

Nilesh Patil↗Ajay Anand↗

arXiv:2508.04243v2 Announce Type: replace-cross Abstract: Angle estimation is an important step in the Doppler ultrasound clinical workflow to measure blood velocity. It is widely recognized that incorrect angle estimation is a leading cause of error in Doppler-based blood velocity measurements. In this paper, we propose a deep learning-based approach for automated Doppler angle estimation. The approach was developed using 2100 human carotid ultrasound images including image augmentation. Five pre-trained models were used to extract images features, and these features were passed to a custom shallow network for Doppler angle estimation. Independently, measurements were obtained by a human observer reviewing the images for comparison. The mean absolute error (MAE) between the automated and manual angle estimates ranged from 3.9{\deg} to 9.4{\deg} for the models evaluated. Furthermore, the MAE for the best performing model was less than the acceptable clinical Doppler angle error threshold thus avoiding misclassification of normal velocity values as a stenosis. The results demonstrate potential for applying a deep-learning based technique for automated ultrasound Doppler angle estimation. Such a technique could potentially be implemented within the imaging software on commercial ultrasound scanners.

Read & Discuss → View Source →

23.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13275

Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing

Authors:

Anugrah Aidin Yotolembah↗Novanto Yudistira↗Gembong Edhi Setyawan↗

This paper presents Custom ZeroCLIP, a retrieval-augmented vision-language framework for zero-shot captioning of Indonesian traditional garments. The dataset contains 3,800 expert-annotated images from all 38 Indonesian provinces. Using a province-level inductive zero-shot protocol, the model is trained on 24 seen provinces, validated on 6 seen provinces, and evaluated on 8 unseen provinces. The framework combines a frozen CLIP ViT-B/32 image encoder, a CLIP text encoder, a BERT text encoder, and an LSTM caption decoder. During inference, unseen-province labels and captions are unavailable, and retrieval uses only captions from training provinces. No unseen-province image, label, or caption is used during training, validation, or retrieval-bank construction. Custom ZeroCLIP achieves a CLIPScore of 0.8536, BLEU-4 of 0.3342, and METEOR of 0.4859, outperforming existing baselines. Ablation results show that retrieval improves cultural vocabulary recovery with a 19.3\% METEOR gain, while human evaluation confirms stronger cultural accuracy and fluency. The results demonstrate the effectiveness of retrieval-augmented domain adaptation for culturally grounded caption generation in low-resource heritage settings. The dataset is publicly available at https://github.com/AnugrahAidinYotolembah/Traditional-Indonesian-Clothing-Captioning-Dataset.

Read & Discuss → View Source →

24.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2601.05895

Diffusion approximations for interacting stochastic systems with reflection and control

Authors:

Thoa Thieu↗Roderick Melnik↗

arXiv:2601.05895v2 Announce Type: replace Abstract: We study diffusion approximations for a class of interacting stochastic systems with reflection and control. Motivated by interacting stochastic dynamics subject to feedback mechanisms and boundary constraints, we consider diffusion-scaled stochastic processes incorporating stochastic fluctuations, state-dependent interactions, and reflection. Under suitable assumptions, we establish convergence in distribution of the scaled processes to systems of interacting reflected stochastic differential equations of Ornstein-Uhlenbeck type. The limiting dynamics capture key features of constrained multi-agent systems, including mean-reverting behavior, interaction effects, and confinement within bounded domains through Skorokhod reflection. The analysis combines diffusion-scaling arguments, stability estimates, and continuity properties of the Skorokhod map to connect discrete stochastic systems with their reflected diffusion limits. To illustrate the framework, we present numerical examples motivated by crowd dynamics and neural population dynamics. The simulations demonstrate qualitative agreement between the finite stochastic systems and the corresponding reflected diffusion models and illustrate how diffusion approximations can provide tractable descriptions of interacting stochastic systems with constraints.

Read & Discuss → View Source →

25.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2511.00802

GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

Authors:

Jie JW Wu↗Ayanda Patrick Herlihy↗Ahmad Saleem Mirza↗Ali Afoud↗Fatemeh Fard↗

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.

Read & Discuss → View Source →