Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to decouple content from presentation, reducing formatting sensitivity. It includes templating for dynamic prompts and a comprehensive developer toolkit (IDE support, SDKs) to improve version control and collaboration. We validate POML through two case studies demonstrating its impact on complex application integration (PomLink) and accuracy performance (TableQA), as well as a user study assessing its effectiveness in real-world development scenarios.

Objective Structured Clinical Examinations (OSCEs) are essential for medical training, but they require significant resources, including professional actors and expert medical feedback. Although Large Language Models (LLMs) have introduced text-based virtual patients for communication practice, these simulations often lack the capability for richer, non-textual interactions. This paper presents a novel framework that significantly enhances LLM-based simulated patients by equipping them with action spaces, thereby enabling more realistic and dynamic patient behaviors that extend beyond text. Furthermore, our system incorporates virtual tutors that provide students with instant, personalized feedback on their performance at any time during these simulated encounters. We have conducted a rigorous evaluation of the framework's real-time performance, including system latency and component accuracy. Preliminary evaluations with medical experts assessed the naturalness and coherence of the simulated patients, as well as the usefulness and appropriateness of the virtual tutor's assessments. This innovative system provides medical students with a low-cost, accessible platform for personalized OSCE preparation at home.

Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously refined and improved. In this process, benchmarks in the scientific domain have played an important role in assessing the reasoning capabilities of MLLMs. However, existing benchmarks still face three key challenges: 1) Insufficient evaluation of models' reasoning abilities in multilingual scenarios; 2) Inadequate assessment of MLLMs' comprehensive modality coverage; 3) Lack of fine-grained annotation of scientific knowledge points. To address these gaps, we propose MME-SCI, a comprehensive and challenging benchmark. We carefully collected 1,019 high-quality question-answer pairs, which involve 3 distinct evaluation modes. These pairs cover four subjects, namely mathematics, physics, chemistry, and biology, and support five languages: Chinese, English, French, Spanish, and Japanese. We conducted extensive experiments on 16 open-source models and 4 closed-source models, and the results demonstrate that MME-SCI is widely challenging for existing MLLMs. For instance, under the Image-only evaluation mode, o4-mini achieved accuracy of only 52.11%, 24.73%, 36.57%, and 29.80% in mathematics, physics, chemistry, and biology, respectively, indicating a significantly higher difficulty level compared to existing benchmarks. More importantly, using MME-SCI's multilingual and fine-grained knowledge attributes, we analyzed existing models' performance in depth and identified their weaknesses in specific domains. The Data and Evaluation Code are available at https://github.com/JCruan519/MME-SCI.

This work revisits and extends synthetic query generation pipelines for Neural Information Retrieval (NIR) by leveraging the InPars Toolkit, a reproducible, end-to-end framework for generating training data using large language models (LLMs). We first assess the reproducibility of the original InPars, InPars-V2, and Promptagator pipelines on the SciFact benchmark and validate their effectiveness using open-source reranker and generator models. Building on this foundation, we introduce two key extensions to the pipeline: (1) fine-tuning a query generator LLM via Contrastive Preference Optimization (CPO) to improve the signal quality in generated queries, and (2) replacing static prompt templates with dynamic, Chain-of-Thought (CoT) optimized prompts using the DSPy framework. Our results show that both extensions reduce the need for aggressive filtering while improving retrieval performance. All code, models, and synthetic datasets are publicly released to support further research at: \href{https://github.com/danilotpnta/IR2-project}{this https URL}.

Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate five storage architectures (Graph Databases, Multi-Model Databases, Data Lakes, Vector Databases, and Time-Series Databases), focusing on their suitability for addressing EAI's core requirements, including physical grounding, low-latency access, and dynamic scalability. We then analyze five retrieval paradigms (Fusion Strategy-Based Retrieval, Representation Alignment-Based Retrieval, Graph-Structure-Based Retrieval, Generation Model-Based Retrieval, and Efficient Retrieval-Based Optimization), revealing a fundamental tension between achieving long-term semantic coherence and maintaining real-time responsiveness. Based on this comprehensive analysis, we identify key bottlenecks, spanning from the foundational Physical Grounding Gap to systemic challenges in cross-modal integration, dynamic adaptation, and open-world generalization. Finally, we outline a forward-looking research agenda encompassing physics-aware data models, adaptive storage-retrieval co-optimization, and standardized benchmarking, to guide future research toward principled data management solutions for EAI. Our survey is based on a comprehensive review of more than 180 related studies, providing a rigorous roadmap for designing the robust, high-performance data management frameworks essential for the next generation of autonomous embodied systems.

The role of large language models (LLMs) in education is increasing, yet little attention has been paid to whether LLM-generated text resembles child language. This study evaluates how LLMs replicate child-like language by comparing LLM-generated texts to a collection of German children's descriptions of picture stories. We generated two LLM-based corpora using the same picture stories and two prompt types: zero-shot and few-shot prompts specifying a general age from the children corpus. We conducted a comparative analysis across psycholinguistic text properties, including word frequency, lexical richness, sentence and word length, part-of-speech tags, and semantic similarity with word embeddings. The results show that LLM-generated texts are longer but less lexically rich, rely more on high-frequency words, and under-represent nouns. Semantic vector space analysis revealed low similarity, highlighting differences between the two corpora on the level of corpus semantics. Few-shot prompt increased similarities between children and LLM text to a minor extent, but still failed to replicate lexical and semantic patterns. The findings contribute to our understanding of how LLMs approximate child language through multimodal prompting (text + image) and give insights into their use in psycholinguistic research and education while raising important questions about the appropriateness of LLM-generated language in child-directed educational tools.

Abstract--Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for the causing of this gap e.g. In the era of foundation models, we show that when leveraging the off-the-shelf (vision) foundation models (e.g., CLIP, DINOv2) for feature extraction, the geometric shapes of the resulting feature distributions exhibit remarkable transferability across domains and datasets. T o verify its practical usefulness, we embody our geometric knowledge-guided distribution calibration framework in two popular and challenging settings: federated learning and long-tailed recognition. In the federated setting, we devise a technique of acquiring the global geometric shape under privacy constraints, then leverage this knowledge to generate new samples for clients, in the aim of bridging the gap between local and global observations. In long-tailed learning, it utilizes the geometric knowledge transferred from sample-rich categories to recover the true distribution for sample-scarce tail classes. Comprehensive experiments show that our proposed geometric knowledge-guided distribution calibration effectively overcomes information deficits caused by data heterogeneity and sample imbalance, with boosted performance across benchmarks. It is often the case that the training data relied upon by models is often only a local [6], sparse [7], and biased observation [8] of the underlying ideal global data distribution. This distribution missing phenomenon manifests in various forms: in federated learning, it appears as label skew and domain skew due to data silos among clients [9], [10], [11], causing a severe misalignment between local data distributions and the global ideal distribution, thereby leading to divergent or even conflicting local optimization directions [12], [13], [14]. In long-tailed recognition, it is characterized by the extreme scarcity of samples in tail classes, preventing the model from capturing the true and complete shape of their distributions [15], [16]. Despite the differing scenarios, the essence is highly unified--models learn from incomplete information, lacking a comprehensive understanding of the overall structure of the real world. Conventional solutions, such as weighting loss functions [7], [17], [18], designing complex regularization terms [9], [14], [19], or aggregation strategies [20], [21], [22], primarily focus on post-hoc compensation at the optimization level. Y anbiao Ma and Zhiwu Lu are with the Gaoling School of Artificial Intelligence, Renmin University of China. Bowen Liu is with T singhua University.

In real-world applications, machine learning models face online label shift, where label distributions change over time. Effective adaptation requires careful learning rate selection: too low slows adaptation and too high causes instability. We propose ASAP (Adaptive Shift Aware Post-training), which dynamically adjusts the learning rate by computing the cosine distance between current and previous unlabeled outputs and mapping it within a bounded range. ASAP requires no labels, model ensembles, or past inputs, using only the previous softmax output for fast, lightweight adaptation. Experiments across multiple datasets and shift scenarios show ASAP consistently improves accuracy and efficiency, making it practical for unsupervised model adaptation.

Consumer agency in the digital age is increasingly constrained by systemic barriers and algorithmic manipulation, raising concerns about the authenticity of consumption choices. Nowadays, financial decisions are shaped by external pressures like obligatory consumption, algorithmic persuasion, and unstable work schedules that erode financial autonomy. Obligatory consumption (like hidden fees) is intensified by digital ecosystems. Algorithmic tactics like personalized recommendations lead to impulsive purchases. Unstable work schedules also undermine financial planning. Thus, it is important to study how these factors impact consumption agency. To do so, we examine formal models grounded in discounted consumption with constraints that bound agency. We construct analytical scenarios in which consumers face obligatory payments, algorithm-influenced impulsive expenses, or unpredictable income due to temporal instability. Using this framework, we demonstrate that even rational, utility-maximizing agents can experience early financial ruin when agency is limited across structural, behavioral, or temporal dimensions and how diminished autonomy impacts long-term financial well-being. Our central argument is that consumer agency must be treated as a value (not a given) requiring active cultivation, especially in digital ecosystems. The connection between our formal modeling and this argument allows us to indicate that limitations on agency (whether structural, behavioral, or temporal) can be rigorously linked to measurable risks like financial instability. This connection is also a basis for normative claims about consumption as a value, by anchoring them in a formally grounded analysis of consumer behavior. As solutions, we study systemic interventions and consumer education to support value deliberation and informed choices. We formally demonstrate how these measures strengthen agency.

In this early study, we observe an Easy-Options Bias (EOB) issue in some multiple-choice Visual Question Answering (VQA) benchmarks such as MMStar, RealWorldQA, SEED-Bench, Next-QA, STAR benchmark and Video-MME. This bias allows vision-language models (VLMs) to select the correct answer using only the vision (V) and options (O) as inputs, without the need for the question (Q). Through grounding experiments, we attribute the bias to an imbalance in visual relevance: the correct answer typically aligns more closely with the visual contents than the negative options in feature space, creating a shortcut for VLMs to infer the answer via simply vision-option similarity matching. To fix this, we introduce GroundAttack, a toolkit that automatically generates hard negative options as visually plausible as the correct answer. We apply it to the NExT-QA and MMStar datasets, creating new EOB-free annotations. On these EOB-free annotations, current VLMs approach to random accuracies under (V+O) settings, and drop to non-saturated accuracies under (V+Q+O) settings, providing a more realistic evaluation of VLMs' QA ability. Codes and new annotations will be released soon.