Abstract--The United States spends more on healthcare than any other nation - nearly 17% of GDP as of the early 2020s - yet struggles with uneven access and outcomes [1] [2]. This paradox of high cost, variable quality, and inequitable access is often described by the "Iron Triangle" of healthcare [3], which posits that improvements in one dimension (access, cost, or quality) often come at the expense of the others. This paper explores how an Intelligent Healthcare Ecosystem (iHE) - an integrated system leveraging advanced technologies and data-driven innovation - can "bend" or even break this iron triangle, enabling simultaneous enhancements in access, cost-efficiency, and quality of care. We review historical and current trends in U.S. healthcare spending, including persistent waste and international comparisons, to underscore the need for transformative change. We then propose a conceptual model and strategic framework for iHE, incorporating emerging technologies such as generative AI and large language models (LLMs), federated learning, interoperability standards (FHIR) and nationwide networks (TEFCA), and digital twins. We introduce an updated healthcare value equation that integrates all three corners of the iron triangle, and we hypothesize that an intelligently coordinated ecosystem can maximize this value by delivering high-quality care to more people at lower cost. Methods include a narrative synthesis of recent literature and policy reports, and Results highlight key components and enabling technologies of an iHE. We discuss how such ecosystems can reduce waste, personalize care, enhance interoperability, and support value-based models, all while addressing challenges like privacy, bias, and stakeholder adoption. The paper is formatted per MDPI guidelines, with APA-style numbered references, illustrative figures (U.S. spending trends, waste breakdown, international spending comparison, conceptual models), equations, and a structured layout. Our findings suggest that embracing an Intelligent Healthcare Ecosystem is pivotal for optimizing the long-standing trade-offs in healthcare's iron triangle, moving towards a system that is more accessible, affordable, and of higher quality for all.

A significant portion of real-world data is inherently represented as textual graphs, and integrating these graphs into large language models (LLMs) is promising to enable complex graph-based question answering. However, a key challenge in LLM-based textual graph QA systems lies in graph retrieval, i.e., how to retrieve relevant content from large graphs that is sufficiently informative while remaining compact for the LLM context. Existing retrievers suffer from poor performance since they either rely on shallow embedding similarity or employ interactive retrieving policies that demand excessive data labeling and training cost. To address these issues, we present Graph-$S^3$, an agentic textual graph reasoning framework that employs an LLM-based retriever trained with synthetic stepwise supervision. Instead of rewarding the agent based on the final answers, which may lead to sparse and unstable training signals, we propose to closely evaluate each step of the retriever based on offline-extracted golden subgraphs. Our main techniques include a data synthesis pipeline to extract the golden subgraphs for reward generation and a two-stage training scheme to learn the interactive graph exploration policy based on the synthesized rewards. Based on extensive experiments on three common datasets in comparison with seven strong baselines, our approach achieves an average improvement of 8.1\% in accuracy and 9.7\% in F$_1$ score. The advantage is even higher in more complicated multi-hop reasoning tasks. Our code will be open-sourced.

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the underlying token distribution is fixed. By sampling softmax denominators from a "calibration text", we can combine together the outputs of multiple such stable heads in the first layer of GPT2-Small, approximating their combined output by a linear summary of the surrounding text. This approximation enables a procedure where from the weights alone - and a single calibration text - we can uncover hundreds of first layer neurons that respond to high-level contextual properties of the surrounding text, including neurons that didn't activate on the calibration text.

LLMs are emerging tools for simulating human behavior in business, economics, and social science, offering a lower-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published experiments in behavioral operations, we assess two criteria: replication of hypothesis-test outcomes and distributional alignment via Wasserstein distance. LLMs reproduce most hypothesis-level effects, capturing key decision biases, but their response distributions diverge from human data, including for strong commercial models. We also test two lightweight interventions -- chain-of-thought prompting and hyperparameter tuning -- which reduce misalignment and can sometimes let smaller or open-source models match or surpass larger systems.

We present VLCAP, an Arabic image captioning framework that integrates CLIP-based visual label retrieval with multimodal text generation. Rather than relying solely on end-to-end captioning, VLCAP grounds generation in interpretable Arabic visual concepts extracted with three multilingual encoders, mCLIP, AraCLIP, and Jina V4, each evaluated separately for label retrieval. A hybrid vocabulary is built from training captions and enriched with about 21K general domain labels translated from the Visual Genome dataset, covering objects, attributes, and scenes. The top-k retrieved labels are transformed into fluent Arabic prompts and passed along with the original image to vision-language models. In the second stage, we tested Qwen-VL and Gemini Pro Vision for caption generation, resulting in six encoder-decoder configurations. The results show that mCLIP + Gemini Pro Vision achieved the best BLEU-1 (5.34%) and cosine similarity (60.01%), while AraCLIP + Qwen-VL obtained the highest LLM-judge score (36.33%). This interpretable pipeline enables culturally coherent and contextually accurate Arabic captions.

Mixture-of-Experts (MoE) models can scale parameter capacity by routing each token to a subset of experts through a learned gate function. While conditional routing reduces training costs, it shifts the burden on inference memory: expert parameters and activations consume memory, limiting the number of experts per device. As tokens are routed, some experts become overloaded while others are underutilized. Because experts are mapped to GPUs, this imbalance translates directly into degraded system performance in terms of latency, throughput, and cost. We present LASER, a plug-and-play, inference-time routing algorithm that balances load while preserving accuracy. LASER adapts to the shape of the gate's score distribution. When scores provide a clear preference, it routes to the strongest experts; when scores are more uniform, it broadens the set of viable experts and routes to the least-loaded among them. Because LASER relies only on gate scores from a trained model, it integrates directly into existing MoE inference pipelines without retraining or finetuning. We evaluate LASER on Mixtral-8x7B and DeepSeek-MoE-16b-chat across four datasets (ARC-Easy, ARC-Challenge, MMLU, and GSM8K). LASER improves load balancing, translating into lower latency and higher throughput, while keeping the accuracy changes negligible.

Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as containers or stable networks, where websites behave deterministically. However, in the real world, users access websites over networks and HTTPS connections that introduce instability from multiple sources: client-side, server-side issues or broader system failures. Moreover, live websites are prone to web attacks such Cross-Site Scripting, as well as general site modifications which can cause unexpected or malicious pop-ups or improper functionality. Our experiments show that introducing WAREX leads to significant drops in task success rates, highlighting the limited robustness of state-of-the-art agents. W eb agents are leaving the lab and entering the wild, but benchmarks give a false sense of reliability. Web agents have emerged as a promising paradigm for automating complex online tasks, attracting significant attention across academia and industry. Recent advances have produced state-of-the-art web agents with diverse designs, ranging from variations in prompting and observation spaces to reinforcement learning-based action policies. Notable examples include SteP (Sodhi et al., 2024), WebNaviX (Shlomov et al., 2024), Agent Q (Putta et al., 2024), and GUI-Owl (Y e et al., 2025), among a myriad others. Large technology companies have also begun deploying production-grade agents, such as OpenAI (2025); Perplexity (2025) and TinyFish (2025).

This paper proposes Edge-FIT (Federated Instruction Tuning on the Edge), a scalable framework for Federated Instruction Tuning (FIT) of Large Language Models (LLMs). Traditional Federated Learning (TFL) methods, like FedAvg, fail when confronted with the massive parameter size of LLMs [3], [6]. Our Edge-FIT framework combines federated learning with 4-bit Quantized Low-Rank Adaptation (QLORA), mitigating the core issues of communication and computational overhead. We demonstrate this by filtering the general-purpose Databricks Dolly 15k dataset for the IoT domain. Experimental results show the Edge-FIT tuned Llama 2(7B) achieves an F1-Score of 0.89. We also demonstrate a viable trade-off using the 3.8B Phi-3-mini model, validating Edge-FIT as a scalable framework for decentralized LLM deployment on home compute gateways.

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data necessitates frequent retraining, which introduces a fundamental tension between inference latency and model accuracy under constrained GPU resources. Existing retraining strategies either delay model updates, over-commit resources to retraining, or overlook iteration-level retraining granularity. In this paper, we identify that iteration-level scheduling is crucial for adapting retraining frequency to model drift without violating service-level objectives (SLOs). We propose MACE, a hybrid LLM system that colocates concurrent inference (prefill, decode) and fine-tuning, with intelligent memory management to maximize task performance while promising inference throughput. MACE leverages the insight that not all model updates equally affect output alignment and allocates GPU cycles accordingly to balance throughput, latency, and update freshness. Our trace-driven evaluation shows that MACE matches or exceeds continuous retraining while reducing inference latency by up to 63% and maintaining throughput under resource constraints. Compared to periodic retraining, MACE improves latency breakdown across prefill, decode, and finetune stages, and sustains GPU utilization above 85% in NVIDIA AGX Orin. These results demonstrate that iteration-level hybrid scheduling is a promising direction for deploying LLMs with continual learning capabilities on edge platforms.

Interpreting language models often involves circuit analysis, which aims to identify sparse subnetworks, or circuits, that accomplish specific tasks. Existing circuit discovery algorithms face a fundamental trade-off: attribution patching is fast but unfaithful to the full model, while edge pruning is faithful but computationally expensive. This research proposes a hybrid attribution and pruning (HAP) framework that uses attribution patching to identify a high-potential subgraph, then applies edge pruning to extract a faithful circuit from it. We show that HAP is 46\% faster than baseline algorithms without sacrificing circuit faithfulness. Furthermore, we present a case study on the Indirect Object Identification task, showing that our method preserves cooperative circuit components (e.g. S-inhibition heads) that attribution patching methods prune at high sparsity. Our results show that HAP could be an effective approach for improving the scalability of mechanistic interpretability research to larger models. Our code is available at https://anonymous.4open.science/r/HAP-circuit-discovery.