arXiv subjects

Aditi Singh

Publications and source records attributed to Aditi Singh.

At least 19 recordsLinked to original sources

arXiv2026

Frontier Orbital Engineering in Heteroatom-Doped Prototypical Organic Dyes for Dye-Sensitized Solar Cells

The computational design of heteroatom-doped organic dyes for dye-sensitized solar cells (DSSCs) remains challenging, as predictive methods must accurately describe long-range charge-transfer (CT) excitations while remaining computationally efficient for systematic materials screening. In this work, we investigate the electronic structure and excited-state properties using the range-separated hybrid functional LC-$ω$PBE in conjunction with linear-response time-dependent density functional theory (TDDFT) within the Tamm-Dancoff approximation (TDA). We employ a simplified, physically motivated, effective tuning protocol ($ω_{eff}$) to enable the rapid and reliable screening of electronic properties of organic dyes. Charge-transfer excitation energies and frontier orbital alignment the key factors governing light absorption and electron injection in DSSCs are analyzed through targeted heteroatom (N, O, and B) incorporation into donor-$π$-acceptor (D-$π$-A) organic dyes. A library of 27 mono-, di-, and tri-doped prototypical organic dyes is designed based on a carbazole donor and a cyanoacrylic acid acceptor through targeted doping at three positions of the $π$-bridge or linker. Distinct design trends emerge: electron-rich nitrogen and oxygen dopants increase the HOMO-LUMO gap and blue-shift CT excitations, with nitrogen exhibiting the strongest effect, whereas electron-deficient boron substitution narrows the gap and induces pronounced red shifts. Notably, the BBN-doped dye exhibits the smallest gap and lowest excitation energy, highlighting boron-rich motifs as promising candidates for enhanced solar light harvesting. Overall, this study establishes transferable heteroatom-doping guidelines and introduces an efficient, reliable, and cost-effective tuned DFT-TDDFT framework for high-throughput computational discovery and optimization of DSSC sensitizers.

physics.chem-ph↗

arXiv2026

Accurate starting points for one-shot $G_0W_0$ and Bethe-Salpeter Equation calculations via effective tuning of range-separated hybrid functionals

The accuracy of one-shot $G_0W_0$ and Bethe-Salpeter equation (BSE) calculations depends strongly on the underlying starting-point eigensystem, which is commonly obtained from a mean-field density-functional approximation. Range-separated hybrid (RSH) functionals provide a particularly effective starting point, however, conventional optimally tuned RSH procedures often require costly, system-specific, multi-step optimizations of the range-separation parameter $ω$. In this work, we show that a recently proposed effective tuning protocol [Singh \textit{et. al.}, Journal of Physical Chemistry Letters, 16, 32, 8198-8208, (2025)] for RSH functionals can serve as an efficient alternative for determining $ω$ used in $G_0W_0$ and BSE calculations. This simplified tuning scheme yields range-separation parameters that are effectively equivalent to those obtained from more elaborate tuning strategies, while avoiding their substantial computational overhead. The resulting tuned RSH eigensystems provide reliable starting points for many-body perturbation theory. In particular, one-shot $G_0W_0$ calculations based on effectively tuned RSH orbitals reproduce reference ionization potentials with high accuracy, while subsequent BSE calculations yield quantitatively reliable neutral excitation energies, optical absorption spectra, and excitonic properties for a diverse set of molecular systems and clusters. These results demonstrate that effective RSH tuning offers a practical and broadly applicable route to accurate quasiparticle and excited-state calculations, combining the accuracy of optimally tuned starting points with the low computational cost required for routine applications of $G_0W_0$ and BSE.

physics.chem-ph↗

arXiv2026

Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs. Retrieval-Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrating real-time data retrieval to provide contextually relevant and up-to-date responses. Despite its promise, traditional RAG systems are constrained by static workflows and lack the adaptability required for multi-step reasoning and complex task management. Agentic Retrieval-Augmented Generation (Agentic RAG) transcends these limitations by embedding autonomous AI agents into the RAG pipeline. These agents leverage agentic design patterns reflection, planning, tool use, and multi-agent collaboration to dynamically manage retrieval strategies, iteratively refine contextual understanding, and adapt workflows through operational structures ranging from sequential steps to adaptive collaboration. This integration enables Agentic RAG systems to deliver flexibility, scalability, and context-awareness across diverse applications. This paper presents an analytical survey of Agentic RAG systems. It traces the evolution of RAG paradigms, introduces a principled taxonomy of Agentic RAG architectures based on agent cardinality, control structure, autonomy, and knowledge representation, and provides a comparative analysis of design trade-offs across existing frameworks. The survey examines applications in healthcare, finance, education, and enterprise document processing, and distills practical lessons for system designers and practitioners. Finally, it identifies key open research challenges related to evaluation, coordination, memory management, efficiency, and governance, outlining directions for future research.

cs.AI↗

arXiv2026

Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents

Large Language Model (LLM)-based agents that plan, use tools and act has begun to shape healthcare and medicine. Reported studies demonstrate competence on various tasks ranging from EHR analysis and differential diagnosis to treatment planning and research workflows. Yet the literature largely consists of overviews which are either broad surveys or narrow dives into a single capability (e.g., memory, planning, reasoning), leaving healthcare work without a common frame. We address this by reviewing 49 studies using a seven-dimensional taxonomy: Cognitive Capabilities, Knowledge Management, Interaction Patterns, Adaptation & Learning, Safety & Ethics, Framework Typology and Core Tasks & Subtasks with 29 operational sub-dimensions. Using explicit inclusion and exclusion criteria and a labeling rubric (Fully Implemented, Partially Implemented, Not Implemented), we map each study to the taxonomy and report quantitative summaries of capability prevalence and co-occurrence patterns. Our empirical analysis surfaces clear asymmetries. For instance, the External Knowledge Integration sub-dimension under Knowledge Management is commonly realized (~76% Fully Implemented) whereas Event-Triggered Activation sub-dimenison under Interaction Patterns is largely absent (~92% Not Implemented) and Drift Detection & Mitigation sub-dimension under Adaptation & Learning is rare (~98% Not Implemented). Architecturally, Multi-Agent Design sub-dimension under Framework Typology is the dominant pattern (~82% Fully Implemented) while orchestration layers remain mostly partial. Across Core Tasks & Subtasks, information centric capabilities lead e.g., Medical Question Answering & Decision Support and Benchmarking & Simulation, while action and discovery oriented areas such as Treatment Planning & Prescription still show substantial gaps (~59% Not Implemented).

cs.AI↗

arXiv2025

Critical Insights into Leading Conversational AI Models

Big Language Models (LLMs) are changing the way businesses use software, the way people live their lives and the way industries work. Companies like Google, High-Flyer, Anthropic, OpenAI and Meta are making better LLMs. So, it's crucial to look at how each model is different in terms of performance, moral behaviour and usability, as these differences are based on the different ideas that built them. This study compares five top LLMs: Google's Gemini, High-Flyer's DeepSeek, Anthropic's Claude, OpenAI's GPT models and Meta's LLaMA. It performs this by analysing three important factors: Performance and Accuracy, Ethics and Bias Mitigation and Usability and Integration. It was found that Claude has good moral reasoning, Gemini is better at multimodal capabilities and has strong ethical frameworks. DeepSeek is great at reasoning based on facts, LLaMA is good for open applications and ChatGPT delivers balanced performance with a focus on usage. It was concluded that these models are different in terms of how well they work, how easy they are to use and how they treat people ethically, making it a point that each model should be utilised by the user in a way that makes the most of its strengths.

cs.AI↗

arXiv2025

Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches

Autonomous AI agents now operate across cloud, enterprise, and decentralized domains, creating demand for registry infrastructures that enable trustworthy discovery, capability negotiation, and identity assurance. We analyze five prominent approaches: (1) MCP Registry (centralized publication of mcp.json descriptors), (2) A2A Agent Cards (decentralized self-describing JSON capability manifests), (3) AGNTCY Agent Directory Service (IPFS Kademlia DHT content routing extended for semantic taxonomy-based content discovery, OCI artifact storage, and Sigstore-backed integrity), (4) Microsoft Entra Agent ID (enterprise SaaS directory with policy and zero-trust integration), and (5) NANDA Index AgentFacts (cryptographically verifiable, privacy-preserving fact model with credentialed assertions). Using four evaluation dimensions: security, authentication, scalability, and maintainability, we surface architectural trade-offs between centralized control, enterprise governance, and distributed resilience. We conclude with design recommendations for an emerging Internet of AI Agents requiring verifiable identity, adaptive discovery flows, and interoperable capability semantics.

cs.NI↗

arXiv2025

Simplified, Physically Motivated, and Broadly Applicable Range-Separation Tuning

Range-separated hybrid functionals (RSH) with ``ionization energy'' and/or ``optimal tuning'' of the screening parameter have proven to be among the most practical and accurate approaches for describing excited-state properties across a wide range of systems, including condensed matter. However, this method typically requires multiple self-consistent calculations and can become computationally expensive and unstable, particularly for extended systems. In this work, we propose a very simple and efficient alternative approach to determine the screening parameter for RSH based solely on the total electron density of the system and the compressibility sum rule of density functional theory (DFT). This effective screening parameter achieves remarkable accuracy, particularly for charge-transfer excitations, surpassing the performance of previously suggested alternatives. Because it relies only on the electron density, the proposed approach is physically transparent and highly practical to automate DFT calculations in large and complex systems, including bulk solids, where ``tuning'' is not possible.

physics.chem-ph↗

arXiv2025

Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Framework

Enhancing clinical decision support (CDS), reducing documentation burdens, and improving patient health literacy remain persistent challenges in digital health. This paper presents an open-source, agent-based framework that integrates Large Language Models (LLMs) with HL7 FHIR data via the Model Context Protocol (MCP) for dynamic extraction and reasoning over electronic health records (EHRs). Built on the established MCP-FHIR implementation, the framework enables declarative access to diverse FHIR resources through JSON-based configurations, supporting real-time summarization, interpretation, and personalized communication across multiple user personas, including clinicians, caregivers, and patients. To ensure privacy and reproducibility, the framework is evaluated using synthetic EHR data from the SMART Health IT sandbox (https://r4.smarthealthit.org/), which conforms to the FHIR R4 standard. Unlike traditional approaches that rely on hardcoded retrieval and static workflows, the proposed method delivers scalable, explainable, and interoperable AI-powered EHR applications. The agentic architecture further supports multiple FHIR formats, laying a robust foundation for advancing personalized digital health solutions.

cs.SE↗

arXiv2025

A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)

Large language model powered autonomous agents demand robust, standardized protocols to integrate tools, share contextual data, and coordinate tasks across heterogeneous systems. Ad-hoc integrations are difficult to scale, secure, and generalize across domains. This survey examines four emerging agent communication protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP), each addressing interoperability in deployment contexts. MCP provides a JSON-RPC client-server interface for secure tool invocation and typed data exchange. ACP defines a general-purpose communication protocol over RESTful HTTP, supporting MIME-typed multipart messages and synchronous and asynchronous interactions. Its lightweight and runtime-independent design enables scalable agent invocation, while features like session management, message routing, and integration with role-based and decentralized identifiers (DIDs). A2A enables peer-to-peer task delegation using capability-based Agent Cards, supporting secure and scalable collaboration across enterprise agent workflows. ANP supports open network agent discovery and secure collaboration using W3C decentralized identifiers DIDs and JSON-LD graphs. The protocols are compared across multiple dimensions, including interaction modes, discovery mechanisms, communication patterns, and security models. Based on the comparative analysis, a phased adoption roadmap is proposed: beginning with MCP for tool access, followed by ACP for structured, multimodal messaging session-aware interaction and both online and offline agent discovery across scalable, HTTP-based deployments A2A for collaborative task execution, and extending to ANP for decentralized agent marketplaces. This work provides a comprehensive foundation for designing secure, interoperable, and scalable ecosystems of LLM-powered agents.

cs.AI↗

arXiv2025

Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks

Large language models (LLMs) have demonstrated impressive performance across a wide range of Natural Language Processing (NLP) tasks. However, ensuring their effectiveness across multiple languages presents unique challenges. Multilingual prompt engineering has emerged as a key approach to enhance LLMs' capabilities in diverse linguistic settings without requiring extensive parameter re-training or fine-tuning. With growing interest in multilingual prompt engineering over the past two to three years, researchers have explored various strategies to improve LLMs' performance across languages and NLP tasks. By crafting structured natural language prompts, researchers have successfully extracted knowledge from LLMs across different languages, making these techniques an accessible pathway for a broader audience, including those without deep expertise in machine learning, to harness the capabilities of LLMs. In this paper, we survey and categorize different multilingual prompting techniques based on the NLP tasks they address across a diverse set of datasets that collectively span around 250 languages. We further highlight the LLMs employed, present a taxonomy of approaches and discuss potential state-of-the-art (SoTA) methods for specific multilingual datasets. Additionally, we derive a range of insights across language families and resource levels (high-resource vs. low-resource), including analyses such as the distribution of NLP tasks by language resource type and the frequency of prompting methods across different language families. Our survey reviews 36 research papers covering 39 prompting techniques applied to 30 multilingual NLP tasks, with the majority of these studies published in the last two years.

cs.CL↗

arXiv2025

Pediatric Asthma Detection with Googles HeAR Model: An AI-Driven Respiratory Sound Classifier

Early detection of asthma in children is crucial to prevent long-term respiratory complications and reduce emergency interventions. This work presents an AI-powered diagnostic pipeline that leverages Googles Health Acoustic Representations (HeAR) model to detect early signs of asthma from pediatric respiratory sounds. The SPRSound dataset, the first open-access collection of annotated respiratory sounds in children aged 1 month to 18 years, is used to extract 2-second audio segments labeled as wheeze, crackle, rhonchi, stridor, or normal. Each segment is embedded into a 512-dimensional representation using HeAR, a foundation model pretrained on 300 million health-related audio clips, including 100 million cough sounds. Multiple classifiers, including SVM, Random Forest, and MLP, are trained on these embeddings to distinguish between asthma-indicative and normal sounds. The system achieves over 91\% accuracy, with strong performance on precision-recall metrics for positive cases. In addition to classification, learned embeddings are visualized using PCA, misclassifications are analyzed through waveform playback, and ROC and confusion matrix insights are provided. This method demonstrates that short, low-resource pediatric recordings, when powered by foundation audio models, can enable fast, noninvasive asthma screening. The approach is especially promising for digital diagnostics in remote or underserved healthcare settings.

cs.SD↗

arXiv2025

Understanding the core limitations of second-order correlation-based functionals through: functional, orbital, and eigenvalue-driven analysis

Density Functional Theory has long struggled to obtain the exact exchange-correlational (XC) functional. Numerous approximations have been designed with the hope of achieving chemical accuracy. However, designing a functional involves numerous methodologies, which has a greater possibility for error accumulation if the functionals are poorly formulated. This study aims to investigate the performance and limitations of second-order correlation functionals within the framework of density functional theory. Specifically, we focus on three major classes of density functional approximations that incorporate second-order energy expressions: \textit{ab initio} (primarily Görling-Levy) functionals, adiabatic connection models, and double-hybrid functionals. The principal objectives of this research are to evaluate the accuracy of second-order correlation functionals, to understand how the choice of reference orbitals and eigenvalues affects the performance of these functionals, to identify the intrinsic limitations of second-order energy expressions, especially when using arbitrary orbitals or non-canonical configurations, and propose strategies for improving their accuracy. By addressing these questions, we aim to provide deeper insights into the factors governing the accuracy of second-order correlation functionals, thereby guiding future functional development.

physics.chem-ph↗

arXiv2025

A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges

Text-to-SQL systems facilitate smooth interaction with databases by translating natural language queries into Structured Query Language (SQL), bridging the gap between non-technical users and complex database management systems. This survey provides a comprehensive overview of the evolution of AI-driven text-to-SQL systems, highlighting their foundational components, advancements in large language model (LLM) architectures, and the critical role of datasets such as Spider, WikiSQL, and CoSQL in driving progress. We examine the applications of text-to-SQL in domains like healthcare, education, and finance, emphasizing their transformative potential for improving data accessibility. Additionally, we analyze persistent challenges, including domain generalization, query optimization, support for multi-turn conversational interactions, and the limited availability of datasets tailored for NoSQL databases and dynamic real-world scenarios. To address these challenges, we outline future research directions, such as extending text-to-SQL capabilities to support NoSQL databases, designing datasets for dynamic multi-turn interactions, and optimizing systems for real-world scalability and robustness. By surveying current advancements and identifying key gaps, this paper aims to guide the next generation of research and applications in LLM-based text-to-SQL systems.

cs.AI↗

arXiv2025

A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges

Large Language Models (LLMs) have transformed numerous domains by providing advanced capabilities in natural language understanding, generation, and reasoning. Despite their groundbreaking applications across industries such as research, healthcare, and creative media, their rapid adoption raises critical concerns regarding sustainability. This survey paper comprehensively examines the environmental, economic, and computational challenges associated with LLMs, focusing on energy consumption, carbon emissions, and resource utilization in data centers. By synthesizing insights from existing literature, this work explores strategies such as resource-efficient training, sustainable deployment practices, and lifecycle assessments to mitigate the environmental impacts of LLMs. Key areas of emphasis include energy optimization, renewable energy integration, and balancing performance with sustainability. The findings aim to guide researchers, practitioners, and policymakers in developing actionable strategies for sustainable AI systems, fostering a responsible and environmentally conscious future for artificial intelligence.

cs.AI↗

arXiv2024

Movie Gen: SWOT Analysis of Meta's Generative AI Foundation Model for Transforming Media Generation, Advertising, and Entertainment Industries

Generative AI is reshaping the media landscape, enabling unprecedented capabilities in video creation, personalization, and scalability. This paper presents a comprehensive SWOT analysis of Metas Movie Gen, a cutting-edge generative AI foundation model designed to produce 1080p HD videos with synchronized audio from simple text prompts. We explore its strengths, including high-resolution video generation, precise editing, and seamless audio integration, which make it a transformative tool across industries such as filmmaking, advertising, and education. However, the analysis also addresses limitations, such as constraints on video length and potential biases in generated content, which pose challenges for broader adoption. In addition, we examine the evolving regulatory and ethical considerations surrounding generative AI, focusing on issues like content authenticity, cultural representation, and responsible use. Through comparative insights with leading models like DALL-E and Google Imagen, this paper highlights Movie Gens unique features, such as video personalization and multimodal synthesis, while identifying opportunities for innovation and areas requiring further research. Our findings provide actionable insights for stakeholders, emphasizing both the opportunities and challenges of deploying generative AI in media production. This work aims to guide future advancements in generative AI, ensuring scalability, quality, and ethical integrity in this rapidly evolving field.

cs.AI↗

arXiv2024

Architectural Flaw Detection in Civil Engineering Using GPT-4

The application of artificial intelligence (AI) in civil engineering presents a transformative approach to enhancing design quality and safety. This paper investigates the potential of the advanced LLM GPT4 Turbo vision model in detecting architectural flaws during the design phase, with a specific focus on identifying missing doors and windows. The study evaluates the model's performance through metrics such as precision, recall, and F1 score, demonstrating AI's effectiveness in accurately detecting flaws compared to human-verified data. Additionally, the research explores AI's broader capabilities, including identifying load-bearing issues, material weaknesses, and ensuring compliance with building codes. The findings highlight how AI can significantly improve design accuracy, reduce costly revisions, and support sustainable practices, ultimately revolutionizing the civil engineering field by ensuring safer, more efficient, and aesthetically optimized structures.

cs.CL↗

arXiv2024

Exploring Prompt Engineering: A Systematic Review with SWOT Analysis

In this paper, we conduct a comprehensive SWOT analysis of prompt engineering techniques within the realm of Large Language Models (LLMs). Emphasizing linguistic principles, we examine various techniques to identify their strengths, weaknesses, opportunities, and threats. Our findings provide insights into enhancing AI interactions and improving language model comprehension of human prompts. The analysis covers techniques including template-based approaches and fine-tuning, addressing the problems and challenges associated with each. The conclusion offers future research directions aimed at advancing the effectiveness of prompt engineering in optimizing human-machine communication.

cs.CL↗

arXiv2024

Encouraging Responsible Use of Generative AI in Education: A Reward-Based Learning Approach

This research introduces an innovative mathematical learning approach that integrates generative AI to cultivate a structured learning rather than quick solution. Our method combines chatbot capabilities and generative AI to offer interactive problem-solving exercises, enhancing learning through a stepby-step approach for varied problems, advocating for the responsible use of AI in education. Our approach emphasizes that immediate answers from ChatGPT can impede real learning. We introduce a reward-based system that requires students to solve mathematical problems effectively to receive the final answer. This encourages a progressive learning path from basic to complex problems, rewarding mastery with final solutions. The goal is to transition students from seeking quick fixes to engaging actively in a comprehensive learning experience.

cs.CY↗