This study evaluates causal reasoning in large language models (LLMs) using 99 clinically grounded laboratory test scenarios aligned with Pearl's Ladder of Causation: association, intervention, and counterfactual reasoning. We examined common laboratory tests such as hemoglobin A1c, creatinine, and vitamin D, and paired them with relevant causal factors including age, gender, obesity, and smoking. Two LLMs - GPT-o1 and Llama-3.2-8b-instruct - were tested, with responses evaluated by four medically trained human experts. GPT-o1 demonstrated stronger discriminative performance (AUROC overall = 0.80 +/- 0.12) compared to Llama-3.2-8b-instruct (0.73 +/- 0.15), with higher scores across association (0.75 vs 0.72), intervention (0.84 vs 0.70), and counterfactual reasoning (0.84 vs 0.69). Sensitivity (0.90 vs 0.84) and specificity (0.93 vs 0.80) were also greater for GPT-o1, with reasoning ratings showing similar trends. Both models performed best on intervention questions and worst on counterfactuals, particularly in altered outcome scenarios. These findings suggest GPT-o1 provides more consistent causal reasoning, but refinement is required before adoption in high-stakes clinical applications.

Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and limited label-preserving augmentations. As a result, ensemble models based on decision trees continue to dominate benchmark leaderboards. In this work, we introduce RuleNet, a transformer-based architecture specifically designed for deep tabular learning. RuleNet incorporates learnable rule embeddings in a decoder, a piecewise linear quantile projection for numerical features, and feature masking ensembles for robustness and uncertainty estimation. Evaluated on eight benchmark datasets, RuleNet matches or surpasses state-of-the-art tree-based methods in most cases, while remaining computationally efficient, offering a practical neural alternative for tabular prediction tasks.

We present UNIPHY+, a unified physiological foundation model (physioFM) framework designed to enable continuous human health and diseases monitoring across care settings using ubiquitously obtainable physiological data. We propose novel strategies for incorporating contextual information during pretraining, fine-tuning, and lightweight model personalization via multi-modal learning, feature fusion-tuning, and knowledge distillation. We advocate testing UNIPHY+ with a broad set of use cases from intensive care to ambulatory monitoring in order to demonstrate that UNIPHY+ can empower generalizable, scalable, and personalized physiological AI to support both clinical decision-making and long-term health monitoring.

Developing trustworthy intelligent vision systems for high-stakes domains, \emph{e.g.}, remote sensing and medical diagnosis, demands broad robustness without costly retraining. We propose \textbf{Visual Reasoning Agent (VRA)}, a training-free, agentic reasoning framework that wraps off-the-shelf vision-language models \emph{and} pure vision systems in a \emph{Think--Critique--Act} loop. While VRA incurs significant additional test-time computation, it achieves up to 40\% absolute accuracy gains on challenging visual reasoning benchmarks. Future work will optimize query routing and early stopping to reduce inference overhead while preserving reliability in vision tasks.

Large Language Models increasingly mediate high-stakes interactions, intensifying research on their capabilities and safety. While recent work has shown that LLMs exhibit consistent and measurable synthetic personality traits, little is known about how modulating these traits affects model behavior. We address this gap by investigating how psychometric personality control grounded in the Big Five framework influences AI behavior in the context of capability and safety benchmarks. Our experiments reveal striking effects: for example, reducing conscientiousness leads to significant drops in safety-relevant metrics on benchmarks such as WMDP, TruthfulQA, ETHICS, and Sycophancy as well as reduction in general capabilities as measured by MMLU. These findings highlight personality shaping as a powerful and underexplored axis of model control that interacts with both safety and general competence. We discuss the implications for safety evaluation, alignment strategies, steering model behavior after deployment, and risks associated with possible exploitation of these findings. Our findings motivate a new line of research on personality-sensitive safety evaluations and dynamic behavioral control in LLMs.

Large Language Model (LLM)-based agents have emerged as a new paradigm that extends LLMs' capabilities beyond text generation to dynamic interaction with external environments. By integrating reasoning with perception, memory, and tool use, agents are increasingly deployed in diverse domains like web navigation and household robotics. A critical challenge, however, lies in ensuring agent generalizability - the ability to maintain consistent performance across varied instructions, tasks, environments, and domains, especially those beyond agents' fine-tuning data. Despite growing interest, the concept of generalizability in LLM-based agents remains underdefined, and systematic approaches to measure and improve it are lacking. In this survey, we provide the first comprehensive review of generalizability in LLM-based agents. We begin by emphasizing agent generalizability's importance by appealing to stakeholders and clarifying the boundaries of agent generalizability by situating it within a hierarchical domain-task ontology. We then review datasets, evaluation dimensions, and metrics, highlighting their limitations. Next, we categorize methods for improving generalizability into three groups: methods for the backbone LLM, for agent components, and for their interactions. Moreover, we introduce the distinction between generalizable frameworks and generalizable agents and outline how generalizable frameworks can be translated into agent-level generalizability. Finally, we identify critical challenges and future directions, including developing standardized frameworks, variance- and cost-based metrics, and approaches that integrate methodological innovations with architecture-level designs. By synthesizing progress and highlighting opportunities, this survey aims to establish a foundation for principled research on building LLM-based agents that generalize reliably across diverse applications.

Medical domain automated text generation is an active area of research and development; however, evaluating the clinical quality of generated reports remains a challenge, especially in instances where domain-specific metrics are lacking, e.g. histopathology. We propose HARE (Histopathology Automated Report Evaluation), a novel entity and relation centric framework, composed of a benchmark dataset, a named entity recognition (NER) model, a relation extraction (RE) model, and a novel metric, which prioritizes clinically relevant content by aligning critical histopathology entities and relations between reference and generated reports. To develop the HARE benchmark, we annotated 813 de-identified clinical diagnostic histopathology reports and 652 histopathology reports from The Cancer Genome Atlas (TCGA) with domain-specific entities and relations. We fine-tuned GatorTronS, a domain-adapted language model to develop HARE-NER and HARE-RE which achieved the highest overall F1-score (0.915) among the tested models. The proposed HARE metric outperformed traditional metrics including ROUGE and Meteor, as well as radiology metrics such as RadGraph-XL, with the highest correlation and the best regression to expert evaluations (higher than the second best method, GREEN, a large language model based radiology report evaluator, by Pearson $r = 0.168$, Spearman $ρ= 0.161$, Kendall $τ= 0.123$, $R^2 = 0.176$, $RMSE = 0.018$). We release HARE, datasets, and the models at https://github.com/knowlab/HARE to foster advancements in histopathology report generation, providing a robust framework for improving the quality of reports.

Imagine AI assistants that enhance conversations without interrupting them: quietly providing relevant information during a medical consultation, seamlessly preparing materials as teachers discuss lesson plans, or unobtrusively scheduling meetings as colleagues debate calendars. While modern conversational LLM agents directly assist human users with tasks through a chat interface, we study this alternative paradigm for interacting with LLM agents, which we call "overhearing agents". Rather than demanding the user's attention, overhearing agents continuously monitor ambient activity and intervene only when they can provide contextual assistance. In this paper, we present the first analysis of overhearing LLM agents as a distinct paradigm in human-AI interaction and establish a taxonomy of overhearing agent interactions and tasks grounded in a survey of works on prior LLM-powered agents and exploratory HCI studies. Based on this taxonomy, we create a list of best practices for researchers and developers building overhearing agent systems. Finally, we outline the remaining research gaps and reveal opportunities for future research in the overhearing paradigm.

Large language models (LLMs) achieve remarkable fluency across linguistic and reasoning tasks but remain systematically prone to hallucination. Prevailing accounts attribute hallucinations to data gaps, limited context, or optimization errors. We argue instead that hallucination is a structural outcome of the transformer architecture. As coherence engines, transformers are compelled to produce fluent continuations, with self-attention simulating the relational structure of meaning but lacking the existential grounding of temporality, mood, and care that stabilizes human understanding. On this basis, we distinguish ontological hallucination, arising when continuations require disclosure of beings in world, and residual reasoning hallucination, where models mimic inference by recycling traces of human reasoning in text. We illustrate these patterns through case studies aligned with Heideggerian categories and an experiment across twelve LLMs showing how simulated "self-preservation" emerges under extended prompts. Our contribution is threefold: (1) a comparative account showing why existing explanations are insufficient; (2) a predictive taxonomy of hallucination linked to existential structures with proposed benchmarks; and (3) design directions toward "truth-constrained" architectures capable of withholding or deferring when disclosure is absent. We conclude that hallucination is not an incidental defect but a defining limit of transformer-based models, an outcome scaffolding can mask but never resolve.

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using meta-tokens, special tokens injected during pre-training, along with a dedicated meta-attention mechanism to guide LMs to use these tokens. We pre-train a language model with a modified GPT-2 architecture equipped with meta-attention in addition to causal multi-head attention, and study the impact of these tokens on a suite of synthetic tasks. We find that data-efficient language model pre-training on fewer than 100B tokens utilizing meta-tokens and our meta-attention mechanism achieves strong performance on these tasks after fine-tuning. We suggest that these gains arise due to the meta-tokens sharpening the positional encoding. This enables them to operate as trainable, content-based landmarks, implicitly compressing preceding context and "caching" it in the meta-token. At inference-time, the meta-token points to relevant context, facilitating length generalization up to 2$\times$ its context window, even after extension with YaRN. We provide further evidence of these behaviors by visualizing model internals to study the residual stream, and assessing the compression quality by information-theoretic analysis on the rate-distortion tradeoff. Our findings suggest that pre-training LMs with meta-tokens offers a simple, data-efficient method to enhance long-context language modeling performance, while introducing new insights into the nature of their behavior towards length generalization.